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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1206
    Prev
    Next
    INDEX
    Explanations

    attends to expressions of desire from related concepts or actions indicated by subsequent tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.01
    1:0.02
    2:0.55
    3:0.02
    4:0.01
    5:0.01
    6:0.04
    7:0.03
    8:0.01
    9:0.01
    10:0.00
    11:0.00
    12:0.01
    13:0.13
    14:0.07
    15:0.01
    Negative Logits
    RectangleBorder
    -0.37
    InputBorder
    -0.33
    Datuak
    -0.32
     $_(
    -0.32
     plufieurs
    -0.32
    OpenHelper
    -0.31
     mijne
    -0.30
     $_"
    -0.30
     kasarigan
    -0.29
    providedIn
    -0.29
    POSITIVE LOGITS
     be
    0.25
     he
    0.24
     it
    0.22
     Said
    0.21
     install
    0.21
     late
    0.21
     Late
    0.21
     Exp
    0.20
     Fra
    0.20
     Wel
    0.20
    Activations Density 0.087%

    No Known Activations