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. 5588
    Prev
    Next
    INDEX
    Explanations

    attends to earlier tokens that are related to "of" from later tokens that often reference "place" or "episodes."

    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
    0:0.09
    1:0.10
    2:0.10
    3:0.08
    4:0.07
    5:0.02
    6:0.14
    7:0.37
    Negative Logits
    دانشنامهٔ
    -0.47
    Personensuche
    -0.41
    tagHelperRunner
    -0.35
    expandindo
    -0.35
    AutoScaleMode
    -0.35
     slightest
    -0.34
     незавершена
    -0.34
     Савезне
    -0.34
    principalTable
    -0.34
     BorderRadius
    -0.33
    POSITIVE LOGITS
    +:+
    0.26
    LayoutPanel
    0.26
    췄
    0.25
     odeur
    0.25
     exitoso
    0.24
    ComponentModel
    0.24
    :`
    0.24
     poitrine
    0.23
    endwhile
    0.23
    wußt
    0.23
    Activations Density 0.344%

    No Known Activations