© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7360
    Prev
    Next
    INDEX
    Explanations

    numeric values in a structured format, possibly statistical data or coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     six
    -0.56
    ?,?,
    -0.55
    पया
    -0.55
     Six
    -0.54
    Six
    -0.54
    "])){
    -0.54
    //}
    
    -0.54
    =?";
    -0.53
     five
    -0.51
    <bos>
    -0.50
    POSITIVE LOGITS
    0
    0.67
     Dure
    0.61
    汰
    0.60
    arrar
    0.59
     Bunker
    0.58
     Shiba
    0.56
    andis
    0.56
    ípio
    0.56
     filters
    0.55
     getItemCount
    0.55
    Activations Density 2.022%

    No Known Activations