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. 6079
    Prev
    Next
    INDEX
    Explanations

    attends to the token "Daniel" from various tokens marked with initials

    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
    0:0.51
    1:0.01
    2:0.03
    3:0.02
    4:0.24
    5:0.10
    6:0.01
    7:0.05
    Negative Logits
     ujednoznacz
    -0.69
    "}")
    -0.61
     وتسجيلات
    -0.60
     tartalomajánló
    -0.58
    AndEndTag
    -0.58
    hematical
    -0.57
     contextLoads
    -0.56
    featureID
    -0.54
    //});
    -0.54
    UnusedPrivate
    -0.54
    POSITIVE LOGITS
    (
    0.38
    ing
    0.36
    .
    0.33
    all
    0.32
    K
    0.31
    in
    0.30
    P
    0.29
    if
    0.29
    U
    0.29
    of
    0.29
    Activations Density 0.003%

    No Known Activations