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. 1306
    Prev
    Next
    INDEX
    Explanations

    attends to tokens related to "company" from various possessive forms of "company."

    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
    2:0.03
    3:0.03
    4:0.00
    5:0.00
    6:0.05
    7:0.05
    8:0.01
    9:0.01
    10:0.01
    11:0.00
    12:0.01
    13:0.07
    14:0.59
    15:0.02
    Negative Logits
    zilla
    -0.29
     autorytatywna
    -0.28
    illa
    -0.27
    ila
    -0.27
    JD
    -0.26
    fork
    -0.26
    ville
    -0.25
    LookAnd
    -0.25
    ILA
    -0.25
    tists
    -0.25
    POSITIVE LOGITS
     desmotivaciones
    0.41
     avoient
    0.38
     Italij
    0.38
     étoient
    0.38
     plufieurs
    0.36
     pouvoit
    0.36
     miniaturka
    0.36
    seamnă
    0.35
     enfans
    0.35
     documentación
    0.34
    Activations Density 0.131%

    No Known Activations