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. 10-GEMMASCOPE-ATT-16K
    6. 5537
    Prev
    Next
    INDEX
    Explanations

    attends to any token governed by a license from any subsequent token that indicates a licensing statement

    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
    0:0.07
    1:0.07
    2:0.52
    3:0.12
    4:0.04
    5:0.03
    6:0.04
    7:0.06
    Negative Logits
    LookAnd
    -0.37
    TabIndex
    -0.29
    UnusedPrivate
    -0.29
    انجليز
    -0.26
    SerializedSize
    -0.26
    Identyfik
    -0.26
     purpoſe
    -0.25
     humide
    -0.24
     /\.(
    -0.24
    MigrationBuilder
    -0.24
    POSITIVE LOGITS
     FetchType
    0.31
     digress
    0.30
    esgue
    0.30
    ymce
    0.29
    }{*}{
    0.29
    InstanceState
    0.29
    rigues
    0.29
     Assisi
    0.28
    sé
    0.28
     springfox
    0.28
    Activations Density 0.085%

    No Known Activations