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. 13405
    Prev
    Next
    INDEX
    Explanations

    assertive statements and transitions in argumentation

    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
     Majefty
    -0.94
     ―――――
    -0.93
    TagMode
    -0.87
    ſelf
    -0.85
    afficheront
    -0.82
     وتسجيلات
    -0.81
    NUMX
    -0.80
    ſelves
    -0.79
    MLLoader
    -0.77
     Houſe
    -0.77
    POSITIVE LOGITS
    ,
    1.51
     we
    1.09
     they
    1.05
     it
    1.04
     there
    0.98
     you
    0.82
     he
    0.75
     if
    0.74
    .
    0.74
     I
    0.71
    Activations Density 0.563%

    No Known Activations