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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 5042
    Prev
    Next
    INDEX
    Explanations

    terms related to critical analysis and evaluations in contexts involving political or social commentary

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

    after a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    science, citations, code, and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     justement
    -1.13
     itſelf
    -1.07
     nemlig
    -1.07
     appunto
    -1.05
     durchaus
    -1.04
     indeed
    -1.02
     effectivement
    -1.00
     ciertamente
    -1.00
     juſt
    -0.99
     essentially
    -0.97
    POSITIVE LOGITS
    .
    0.76
     
    0.60
     die
    0.53
     til
    0.50
     il
    0.50
    哭了
    0.48
     died
    0.47
    ыре
    0.46
    Демографія
    0.46
    ranean
    0.45
    Activations Density 2.669%

    No Known Activations