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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5087
    Prev
    Next
    INDEX
    Explanations

    punctuation used to denote results or conclusions in scientific writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ly
    -0.58
    ch
    -0.53
    /
    -0.53
    <u>
    -0.52
    st
    -0.52
    de
    -0.47
    ment
    -0.47
    cito
    -0.46
    al
    -0.46
    ord
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    1.21
    expandindo
    1.06
     تانيه
    1.02
     ExecuteAsync
    1.01
     فريبيس
    0.96
    }}$\\
    0.95
     المعيارى
    0.94
     nakalista
    0.90
     مشين
    0.87
     مرئيه
    0.86
    Activations Density 0.088%

    No Known Activations