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-2-2B
    4. Attention Out - 16k
    5. 10-GEMMASCOPE-ATT-16K
    6. 6191
    Prev
    Next
    INDEX
    Explanations

    attends to the tokens indicating correctional facilities from tokens indicating inmate status

    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
    0:0.10
    1:0.15
    2:0.16
    3:0.13
    4:0.12
    5:0.06
    6:0.10
    7:0.14
    Negative Logits
     Bader
    -0.24
    σμο
    -0.23
    ")"
    -0.22
    *********/
    -0.22
    !("{}",
    -0.21
    kusen
    -0.21
    bbene
    -0.21
     Rima
    -0.21
    toro
    -0.20
    rids
    -0.20
    POSITIVE LOGITS
     Walkover
    0.36
     समीक्षाओं
    0.36
    LookAnd
    0.35
    RenderAtEndOf
    0.35
    fjspx
    0.31
    TemporalType
    0.30
     poveznice
    0.30
    setVerticalGroup
    0.30
     onAnimation
    0.30
    jooq
    0.30
    Activations Density 0.398%

    No Known Activations