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. 6629
    Prev
    Next
    INDEX
    Explanations

    attends to quotation marks or punctuation from associated clauses or phrases

    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
    0:0.05
    1:0.06
    2:0.06
    3:0.06
    4:0.07
    5:0.03
    6:0.49
    7:0.14
    Negative Logits
    tagHelperRunner
    -0.48
    !*\
    -0.47
     defStyle
    -0.45
    LookAnd
    -0.42
    fjspx
    -0.42
    PYX
    -0.39
    UserScript
    -0.38
    Gön
    -0.36
    ServletConfig
    -0.36
     modalités
    -0.36
    POSITIVE LOGITS
    Hentet
    0.38
    fromnode
    0.33
    %",
    0.33
    ?}",
    0.32
     Waray
    0.31
    StoryboardSegue
    0.31
    ".
    0.30
     GenerationType
    0.30
    äinen
    0.30
    loroethene
    0.30
    Activations Density 0.568%

    No Known Activations