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. 5296
    Prev
    Next
    INDEX
    Explanations

    attends to the numeric sequence "3 09" from specific numeric tokens that follow it

    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
    0:0.14
    1:0.11
    2:0.10
    3:0.06
    4:0.07
    5:0.12
    6:0.04
    7:0.32
    Negative Logits
    AndEndTag
    -0.38
    rungsseite
    -0.28
    Einzelnachweise
    -0.27
    ContentAlignment
    -0.26
    Reprints
    -0.25
    SequentialGroup
    -0.25
    StoryboardSegue
    -0.25
    Formazione
    -0.24
     estimés
    -0.24
     aapt
    -0.24
    POSITIVE LOGITS
    fraz
    0.35
     समीक्षाओं
    0.33
     uncin
    0.30
     Efq
    0.30
     faſt
    0.28
     Ogle
    0.28
     verdaderamente
    0.28
     greateſt
    0.28
     Reſ
    0.28
     poffe
    0.28
    Activations Density 0.006%

    No Known Activations