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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1297
    Prev
    Next
    INDEX
    Explanations

    attends to the token "solely" from a related context of dependence or restriction indicated by later tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.02
    1:0.02
    2:0.07
    3:0.02
    4:0.00
    5:0.02
    6:0.04
    7:0.04
    8:0.01
    9:0.01
    10:0.01
    11:0.01
    12:0.04
    13:0.54
    14:0.06
    15:0.01
    Negative Logits
    ↵↵
    -0.26
    来
    -0.16
    <eos>
    -0.15
     Krü
    -0.15
    以
    -0.15
     sne
    -0.14
    作
    -0.14
    <strong>
    -0.14
    至
    -0.14
     Lieben
    -0.14
    POSITIVE LOGITS
    featureID
    0.45
    ThroughAttribute
    0.42
    MessageOf
    0.40
    Personensuche
    0.37
     مرئيه
    0.36
     ویکی‌پدی
    0.36
    SharedDtor
    0.35
    دانشنامهٔ
    0.35
    MemoryWarning
    0.34
    IndentedString
    0.34
    Activations Density 1.665%

    No Known Activations