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. 0-GEMMASCOPE-ATT-16K
    6. 6172
    Prev
    Next
    INDEX
    Explanations

    attends to contexts indicating minimal thresholds from contexts suggesting variability or multiple options

    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
    0:0.05
    1:0.03
    2:0.05
    3:0.03
    4:0.63
    5:0.06
    6:0.04
    7:0.08
    Negative Logits
    NUMX
    -0.49
     crdi
    -0.44
    StateToProps
    -0.43
    ^(@)
    -0.42
     ſeveral
    -0.42
    angliski
    -0.42
    près
    -0.41
     estekak
    -0.41
     وتسجيلات
    -0.41
     siguran
    -0.40
    POSITIVE LOGITS
     افتراض
    0.40
    InSection
    0.37
    byshev
    0.33
    ArgumentParser
    0.33
    enderror
    0.32
     sk
    0.31
    requestCode
    0.31
    homonymie
    0.31
    WebServlet
    0.30
    parsedMessage
    0.30
    Activations Density 0.067%

    No Known Activations