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. 1267
    Prev
    Next
    INDEX
    Explanations

    attends to names marked with brackets from related tokens marked with double square brackets

    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
    0:0.00
    1:0.00
    2:0.58
    3:0.15
    4:0.00
    5:0.00
    6:0.02
    7:0.01
    8:0.00
    9:0.00
    10:0.00
    11:0.00
    12:0.00
    13:0.07
    14:0.07
    15:0.00
    Negative Logits
    ConstraintMaker
    -0.35
     actionMode
    -0.28
    новништво
    -0.25
    djangoproject
    -0.24
    stateProvider
    -0.22
    RegressionTest
    -0.22
     kasarigan
    -0.22
     AppCompatTheme
    -0.21
     ExecuteAsync
    -0.21
    lery
    -0.21
    POSITIVE LOGITS
    localctx
    0.42
    Хьажоргаш
    0.38
    openConnection
    0.37
    сылкі
    0.36
    haram
    0.36
    COLN
    0.35
    ParseTree
    0.35
     demografica
    0.35
    dataclass
    0.35
    unknown
    0.35
    Activations Density 1.665%

    No Known Activations