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. 9284
    Prev
    Next
    INDEX
    Explanations

    terms related to liability and financial responsibility in contexts such as insurance and legal matters

    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
    enumii
    -0.64
    /*
    -0.63
    DockStyle
    -0.61
     gigantic
    -0.60
     whatnot
    -0.57
    enumi
    -0.56
     enormous
    -0.56
     enorme
    -0.55
    Huge
    -0.55
    GenerationType
    -0.54
    POSITIVE LOGITS
     almeno
    2.37
     atleast
    2.33
    至少
    2.23
     mindestens
    2.08
     setidaknya
    1.90
     حداقل
    1.88
     minimum
    1.79
    少なくとも
    1.78
     wenigstens
    1.61
     mínimo
    1.53
    Activations Density 0.912%

    No Known Activations