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-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 6040
    Prev
    Next
    INDEX
    Explanations

    attends to the token "в" from the token "конце" in the context of coding and mathematical discussions

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 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
    0:0.10
    1:0.03
    2:0.06
    3:0.03
    4:0.56
    5:0.08
    6:0.05
    7:0.05
    Negative Logits
     and
    -0.38
     in
    -0.37
     
    -0.33
     at
    -0.32
     the
    -0.32
     for
    -0.32
     в
    -0.31
     (
    -0.31
     on
    -0.29
     a
    -0.29
    POSITIVE LOGITS
     surla
    0.55
     Paglinawan
    0.53
    interopRequire
    0.50
     doubtnut
    0.50
     disambiguazione
    0.48
     Anſ
    0.48
    EDEFAULT
    0.47
     Forumite
    0.47
    LookAnd
    0.47
    >\<^
    0.47
    Activations Density 0.020%

    No Known Activations