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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6393
    Prev
    Next
    INDEX
    Explanations

    attends to the closing braces of various namespaces from the opening namespace tokens

    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
    0:0.11
    1:0.14
    2:0.12
    3:0.11
    4:0.12
    5:0.08
    6:0.14
    7:0.16
    Negative Logits
    !';
    -0.32
    новништво
    -0.30
    [{\
    -0.29
    ...');
    -0.29
    [-\
    -0.29
    ilarang
    -0.29
    <!--[
    -0.28
    WriteBarrier
    -0.28
    ;->
    -0.28
    jusqu
    -0.27
    POSITIVE LOGITS
     Drapeau
    0.32
    帖最后由
    0.31
     خارجية
    0.31
     متعلقه
    0.31
    ReusableCell
    0.28
     Jolla
    0.27
    enumi
    0.26
    PRNewswire
    0.26
     تانيه
    0.25
    tvguidetime
    0.25
    Activations Density 0.002%

    No Known Activations