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. 21-GEMMASCOPE-RES-16K
    6. 540
    Prev
    Next
    INDEX
    Explanations

    special formatting or markers in textual content, such as code or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendriers
    -0.88
    />";
    -0.80
    +#+
    -0.78
    Hentet
    -0.77
     ModelExpression
    -0.75
     كومونز
    -0.72
    !';
    -0.72
    >";
    
    -0.71
    SequentialGroup
    -0.70
     ProtoMessage
    -0.69
    POSITIVE LOGITS
    0
    0.67
    .
    0.67
    2
    0.65
    5
    0.63
    1
    0.62
    4
    0.59
    6
    0.59
    8
    0.59
    3
    0.59
    7
    0.57
    Activations Density 0.415%

    No Known Activations