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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 227
    Prev
    Next
    INDEX
    Explanations

    attends to the keyword "Public" from associated health and safety tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    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

    Head Attr Weights
    0:0.26
    1:0.01
    2:0.03
    3:0.01
    4:0.26
    5:0.34
    6:0.02
    7:0.03
    Negative Logits
     verst
    -0.41
    ]][
    -0.41
    pinos
    -0.40
     Debates
    -0.40
     Theories
    -0.40
     Treatments
    -0.40
    ORT
    -0.39
    ']>;
    -0.39
     Approaches
    -0.39
     lachen
    -0.39
    POSITIVE LOGITS
    Autoritní
    0.39
     متعلقه
    0.39
    GraphicsUnit
    0.38
     الحره
    0.33
    EndContext
    0.33
    انتهای
    0.33
     ModelExpression
    0.31
     ExecuteAsync
    0.30
    ScopeManager
    0.30
    Koordinaten
    0.29
    Activations Density 0.101%

    No Known Activations