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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1204
    Prev
    Next
    INDEX
    Explanations

    attends to pronouns referring to unspecified subjects from verbs expressing necessity or requirement

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    3:0.01
    4:0.01
    5:0.03
    6:0.15
    7:0.09
    8:0.01
    9:0.01
    10:0.03
    11:0.02
    12:0.02
    13:0.30
    14:0.10
    15:0.04
    Negative Logits
     pleaſure
    -0.25
     transformation
    -0.24
     release
    -0.24
     meta
    -0.24
     scale
    -0.24
     draft
    -0.24
     insign
    -0.23
     final
    -0.23
     modification
    -0.23
    DataURL
    -0.23
    POSITIVE LOGITS
    httphttps
    0.35
     wikipagina
    0.33
     Taktlose
    0.31
     Comprometido
    0.30
     něko
    0.30
     noDo
    0.30
     tė
    0.28
    
    0.28
     meeste
    0.28
     resourceCulture
    0.28
    Activations Density 0.158%

    No Known Activations