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. 20-GEMMASCOPE-RES-16K
    6. 2066
    Prev
    Next
    INDEX
    Explanations

    references to charts, diagrams, and visual data representations

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

    Refers to items visually depicted

    np_acts-logits-general · gemini-2.0-flash

    pointing to something below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.72
    Portale
    -0.60
    sidemargin
    -0.60
    }/${
    -0.56
    KommentareTeilen
    -0.52
     '',
    
    -0.50
    Xna
    -0.48
    FetchType
    -0.48
    долго
    -0.48
    DllImport
    -0.47
    POSITIVE LOGITS
     below
    3.45
    below
    2.83
     Below
    2.60
     BELOW
    2.51
    Below
    2.46
     above
    2.19
     abaixo
    2.08
     bellow
    2.07
     ниже
    1.93
     poniżej
    1.90
    Activations Density 0.560%

    No Known Activations