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. 6171
    Prev
    Next
    INDEX
    Explanations

    attends to cohomology-related tokens from semiample tokens

    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
    0:0.02
    1:0.02
    2:0.05
    3:0.36
    4:0.11
    5:0.09
    6:0.23
    7:0.08
    Negative Logits
    ↵↵
    -0.43
    re
    -0.25
    ia
    -0.24
    “
    -0.24
    <eos>
    -0.23
    am
    -0.23
     this
    -0.23
    ഞ്
    -0.22
    ne
    -0.22
     a
    -0.22
    POSITIVE LOGITS
    TagMode
    0.54
    IntoConstraints
    0.51
     gynhyrchwyd
    0.46
     виправивши
    0.45
     дописавши
    0.45
    providedIn
    0.44
    AccessorTable
    0.43
    migrationBuilder
    0.43
    ChildScrollView
    0.42
     AppColors
    0.42
    Activations Density 0.132%

    No Known Activations