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. 6153
    Prev
    Next
    INDEX
    Explanations

    attends to overrides from corresponding tokens that provide the context for those overrides

    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
    0:0.06
    1:0.59
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.05
    7:0.06
    Negative Logits
    drawSprites
    -0.41
     Majefty
    -0.38
    ########.
    -0.37
    LookAnd
    -0.35
    +#+#
    -0.35
    EndGlobalSection
    -0.34
    mstyle
    -0.34
    PageContext
    -0.33
     quæ
    -0.33
     LIRE
    -0.33
    POSITIVE LOGITS
    <strong>
    0.27
    onAttach
    0.26
    <em>
    0.25
    •
    0.25
     الرياضيه
    0.25
     fopen
    0.22
    1
    0.21
     “
    0.21
     be
    0.21
     ع
    0.21
    Activations Density 0.010%

    No Known Activations