Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Attention Out - 16k
    5. 10-GEMMASCOPE-ATT-16K
    6. 6539
    Prev
    Next
    INDEX
    Explanations

    attends to code-related commands or sections marked for development from a title or header in the documentation

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.06
    1:0.09
    2:0.08
    3:0.13
    4:0.11
    5:0.04
    6:0.30
    7:0.14
    Negative Logits
    Xna
    -0.43
    ngrx
    -0.40
    djangoproject
    -0.40
    //
    -0.39
    XmlAccessType
    -0.35
    談社
    -0.35
     MonoBehaviour
    -0.34
    migrationBuilder
    -0.33
    Portale
    -0.33
    Ligações
    -0.33
    POSITIVE LOGITS
     Horses
    0.41
     Breen
    0.38
    avir
    0.37
     Races
    0.36
    :])
    0.36
    FFIX
    0.36
     Ressourcen
    0.35
    QRST
    0.34
    imageio
    0.34
    Beli
    0.34
    Activations Density 0.117%

    No Known Activations