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. 1368
    Prev
    Next
    INDEX
    Explanations

    attends to the programming language "java" from technical terminology tokens related to coding and libraries

    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
    1:0.01
    2:0.66
    3:0.03
    4:0.00
    5:0.00
    6:0.01
    7:0.01
    8:0.00
    9:0.01
    10:0.00
    11:0.00
    12:0.00
    13:0.11
    14:0.05
    15:0.00
    Negative Logits
    RectangleBorder
    -0.37
    styleType
    -0.29
    ViewFeatures
    -0.28
    >{@
    -0.28
    RenderAtEndOf
    -0.27
    ValueGeneration
    -0.26
    SourceChecksum
    -0.26
    MigrationBuilder
    -0.25
    AutoScaleMode
    -0.25
    GraphicsUnit
    -0.25
    POSITIVE LOGITS
     Administrativna
    0.29
    <eos>
    0.28
    Evaluating
    0.27
    unked
    0.27
    oubted
    0.27
    actéristi
    0.27
    arangay
    0.26
     Kraw
    0.26
    ENEFITS
    0.26
    evalu
    0.26
    Activations Density 3.413%

    No Known Activations