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. 1188
    Prev
    Next
    INDEX
    Explanations

    attends to the token "without" from the corresponding tokens indicating lack of knowledge or awareness

    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
    0:0.01
    1:0.01
    2:0.02
    3:0.02
    4:0.01
    5:0.01
    6:0.67
    7:0.06
    8:0.00
    9:0.01
    10:0.00
    11:0.00
    12:0.01
    13:0.02
    14:0.07
    15:0.01
    Negative Logits
     kasarigan
    -0.78
     Bewußt
    -0.71
     asamblea
    -0.63
    pulseira
    -0.63
    uxxxx
    -0.62
    pecabe
    -0.62
     gruesa
    -0.61
     desmotivaciones
    -0.60
     nocturno
    -0.60
     plegable
    -0.59
    POSITIVE LOGITS
    lund
    0.45
    $
    0.45
    bri
    0.44
    Sp
    0.44
    BP
    0.44
    pag
    0.44
    ge
    0.44
    gr
    0.44
    bil
    0.44
    arg
    0.43
    Activations Density 0.085%

    No Known Activations