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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6182
    Prev
    Next
    INDEX
    Explanations

    attends to the token "NS" from instances of "NS" in various programming contexts

    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
    0:0.03
    1:0.47
    2:0.17
    3:0.03
    4:0.06
    5:0.05
    6:0.03
    7:0.11
    Negative Logits
    .
    -0.54
    ,
    -0.48
    2
    -0.40
    1
    -0.39
    3
    -0.39
    N
    -0.38
     (
    -0.38
    H
    -0.37
    h
    -0.37
    _
    -0.36
    POSITIVE LOGITS
    parsedMessage
    0.91
    GEBURTSDATUM
    0.79
    abestanden
    0.78
     '\\;'
    0.75
    ագրություններ
    0.73
    ^(@)
    0.73
    NUMX
    0.73
    '},
    
    0.73
    findpost
    0.72
    providedIn
    0.71
    Activations Density 0.028%

    No Known Activations