Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6046
    Prev
    Next
    INDEX
    Explanations

    attends to ordinal indicators (like "2nd" or "3rd") from corresponding time or date indicators (like "December")

    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
    0:0.09
    1:0.03
    2:0.02
    3:0.02
    4:0.18
    5:0.53
    6:0.06
    7:0.04
    Negative Logits
    enumi
    -0.55
    MigrationBuilder
    -0.52
    awtextra
    -0.45
     beginnetje
    -0.41
    kloped
    -0.40
    tvguidetime
    -0.40
    KommentareTeilen
    -0.39
    Personendaten
    -0.39
    WebVitals
    -0.38
    sidemargin
    -0.38
    POSITIVE LOGITS
    quê
    0.30
     Piro
    0.27
     lectured
    0.26
     desertion
    0.26
     scaven
    0.26
     Crown
    0.26
    upné
    0.25
     Njema
    0.25
     princí
    0.25
     Soriano
    0.25
    Activations Density 0.008%

    No Known Activations