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. 5476
    Prev
    Next
    INDEX
    Explanations

    attends to performance metrics, such as rebounds and assists, from corresponding metric indicators, such as points and steals

    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
    0:0.09
    1:0.11
    2:0.10
    3:0.16
    4:0.13
    5:0.03
    6:0.18
    7:0.15
    Negative Logits
    RectangleBorder
    -0.38
    EndProject
    -0.33
    AndEndTag
    -0.31
    InputBorder
    -0.28
    خانه
    -0.28
    omé
    -0.28
     Occidental
    -0.28
     Kork
    -0.28
    HasKey
    -0.28
     بيها
    -0.27
    POSITIVE LOGITS
    Notae
    0.32
    autorelease
    0.31
    quelize
    0.30
    lccn
    0.29
    etheless
    0.28
    āda
    0.28
     StringTokenizer
    0.28
    providedIn
    0.28
    ślę
    0.27
     LUMP
    0.27
    Activations Density 0.096%

    No Known Activations