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. 1330
    Prev
    Next
    INDEX
    Explanations

    attends to company-related tokens from corresponding legal actions or references

    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
    2:0.13
    3:0.02
    4:0.00
    5:0.01
    6:0.04
    7:0.06
    8:0.01
    9:0.03
    10:0.01
    11:0.00
    12:0.01
    13:0.39
    14:0.16
    15:0.01
    Negative Logits
     Bic
    -0.61
     Py
    -0.61
     Ox
    -0.61
     Gy
    -0.61
     Mat
    -0.60
    ery
    -0.59
    ux
    -0.59
    lan
    -0.59
    ons
    -0.59
     Ad
    -0.59
    POSITIVE LOGITS
     Italij
    0.66
     plegable
    0.58
     invasión
    0.58
     negociación
    0.58
     Económica
    0.57
     Infór
    0.57
     colgante
    0.57
     láser
    0.57
     civilización
    0.56
     desmotivaciones
    0.55
    Activations Density 0.159%

    No Known Activations