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. 1329
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.05
    1:0.06
    2:0.07
    3:0.05
    4:0.04
    5:0.05
    6:0.05
    7:0.05
    8:0.06
    9:0.06
    10:0.07
    11:0.04
    12:0.09
    13:0.06
    14:0.05
    15:0.05
    Negative Logits
    ,
    -1.00
     Quad
    -0.73
     Fac
    -0.73
     Dex
    -0.72
     Tex
    -0.72
     Dura
    -0.71
     Vac
    -0.71
     Lex
    -0.71
     Inf
    -0.71
     Rel
    -0.71
    POSITIVE LOGITS
     Wikiseite
    0.55
     Menschheit
    0.53
     Notwendigkeit
    0.53
     Económica
    0.51
     Verhältnisse
    0.51
     setempat
    0.50
     Absicht
    0.50
     vuestros
    0.49
     Gerechtigkeit
    0.49
     Öffentlichkeit
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.