Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6896
    Prev
    Next
    INDEX
    Explanations

    references or citations to academic papers, particularly those with "GP" in the identifier.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @jbloomaus

    abbreviations and acronyms related to genetic research and technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to specific sections, theorems, equations, or numerical properties in scientific and mathematical texts.

    oai_token-act-pair · gpt-4oTriggered by @bot

    This neuron seems to activate for the presence of mathematical formulas and technical jargon, particularly related to mathematical sequences and their properties. It seems to be picking up on the formal language and symbolic representation common in mathematical texts.

    oai_token-act-pair · gemini-1.5-proTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.52
    UrlResolution
    -0.50
     referenties
    -0.47
    hidupan
    -0.47
    expandindo
    -0.47
    клопе
    -0.46
     chofe
    -0.46
     Selby
    -0.45
     poffible
    -0.45
     Abbé
    -0.45
    POSITIVE LOGITS
     GS
    1.54
     GV
    1.51
     GA
    1.50
     G
    1.46
     GL
    1.45
     GF
    1.44
    GF
    1.44
     Ga
    1.42
     Gu
    1.41
     GC
    1.41
    Activations Density 1.326%

    No Known Activations