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. 6553
    Prev
    Next
    INDEX
    Explanations

    attends to the token "also" from citations or mentions of specific cases or authors

    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
    0:0.08
    1:0.09
    2:0.08
    3:0.08
    4:0.07
    5:0.03
    6:0.16
    7:0.37
    Negative Logits
     oprot
    -0.41
    contentLoaded
    -0.40
    RegistryLite
    -0.39
    Autoritní
    -0.38
    ContentAsync
    -0.38
    TestTools
    -0.37
    Traducción
    -0.36
     ModelExpression
    -0.35
     externi
    -0.35
     ویکی‌پدی
    -0.34
    POSITIVE LOGITS
    migrationBuilder
    0.32
    rimos
    0.31
     GenerationType
    0.30
    ConstraintMaker
    0.30
    réhen
    0.28
    ezers
    0.28
    ↓↓↓
    0.27
     sputnik
    0.27
    alignSelf
    0.26
     przecież
    0.26
    Activations Density 0.497%

    No Known Activations