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. 1354
    Prev
    Next
    INDEX
    Explanations

    attends to the concept of "probable cause" from various contexts related to "showing" or "show."

    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
    0:0.07
    1:0.11
    2:0.01
    3:0.02
    4:0.02
    5:0.03
    6:0.04
    7:0.03
    8:0.08
    9:0.04
    10:0.04
    11:0.02
    12:0.26
    13:0.08
    14:0.02
    15:0.06
    Negative Logits
     (
    -0.53
     of
    -0.48
    -
    -0.47
     Table
    -0.46
     such
    -0.46
     in
    -0.44
     $\
    -0.43
     Figure
    -0.43
     '
    -0.43
    .
    -0.43
    POSITIVE LOGITS
    ſelf
    0.68
    
    0.63
    tagHelperRunner
    0.60
    ſelves
    0.57
     Houſe
    0.56
     myſelf
    0.56
     houſe
    0.51
     فريبيس
    0.49
     itſelf
    0.48
     للمعارف
    0.48
    Activations Density 0.011%

    No Known Activations