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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-ATT-16K
    6. 6371
    Prev
    Next
    INDEX
    Explanations

    attends to numeric tokens associated with other numeric representations

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/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.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.12
    1:0.12
    2:0.13
    3:0.13
    4:0.10
    5:0.11
    6:0.11
    7:0.14
    Negative Logits
    WriteLiteral
    -0.39
     kysy
    -0.34
    HttpGet
    -0.31
     geb
    -0.31
    ubuntu
    -0.30
    gena
    -0.29
     <<<<<<<<<<<<<<
    -0.29
    offre
    -0.28
     Doh
    -0.28
    <?,
    -0.28
    POSITIVE LOGITS
    Vidite
    0.42
     ExecuteAsync
    0.40
     تانيه
    0.32
    HasBeenSet
    0.31
    EndGlobalSection
    0.31
     HasFactory
    0.31
    ConverterFactory
    0.30
     Versuche
    0.30
    EDEFAULT
    0.29
    HostException
    0.28
    Activations Density 0.074%

    No Known Activations