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. 6151
    Prev
    Next
    INDEX
    Explanations

    attends to non-related tokens from grappling with tokens

    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
    0:0.08
    1:0.20
    2:0.16
    3:0.08
    4:0.10
    5:0.25
    6:0.04
    7:0.06
    Negative Logits
    GEBURTSDATUM
    -0.54
    contentLoaded
    -0.47
    SourceChecksum
    -0.46
     protoimpl
    -0.44
     Signalez
    -0.41
    MigrationBuilder
    -0.41
    parsedMessage
    -0.38
    حوالہ
    -0.38
     utafitiHapana
    -0.37
    __*/
    -0.37
    POSITIVE LOGITS
     viewWillAppear
    0.22
    wikkeld
    0.21
     gambe
    0.21
    spaceBetween
    0.21
     ayr
    0.21
    /
    0.20
     effective
    0.20
     "
    0.20
     (
    0.20
     menemp
    0.20
    Activations Density 0.000%

    No Known Activations