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. 1173
    Prev
    Next
    INDEX
    Explanations

    attends to "util" from programming or related types from tokens concerning technical aspects or functionalities

    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
    0:0.05
    1:0.03
    2:0.00
    3:0.01
    4:0.01
    5:0.02
    6:0.02
    7:0.02
    8:0.07
    9:0.43
    10:0.13
    11:0.04
    12:0.03
    13:0.02
    14:0.01
    15:0.01
    Negative Logits
     queſta
    -0.78
     autorytatywna
    -0.71
     plufieurs
    -0.63
     myſelf
    -0.62
     ſind
    -0.62
    ſelf
    -0.62
    Personensuche
    -0.61
    <unused43>
    -0.60
    <unused41>
    -0.60
    <unused8>
    -0.60
    POSITIVE LOGITS
    ↵
    0.40
     \
    0.34
    0
    0.33
    1
    0.32
    ou
    0.30
    ta
    0.30
    fo
    0.30
    ↵↵
    0.30
     the
    0.30
    ti
    0.29
    Activations Density 0.072%

    No Known Activations