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. 1250
    Prev
    Next
    INDEX
    Explanations

    attends to the second instance of the previous backslash from the second instance of the subsequent square brackets

    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
    0:0.00
    1:0.01
    2:0.64
    3:0.01
    4:0.00
    5:0.00
    6:0.05
    7:0.01
    8:0.01
    9:0.00
    10:0.03
    11:0.00
    12:0.00
    13:0.01
    14:0.12
    15:0.01
    Negative Logits
    begin
    -0.45
    mathrm
    -0.42
     \
    -0.34
    </tbody>
    -0.34
    ↵
    -0.34
    end
    -0.33
                                   
    -0.32
                                 
    -0.32
               
    -0.31
                           
    -0.30
    POSITIVE LOGITS
    pulseira
    0.46
    iſen
    0.46
    ſcher
    0.45
    bricas
    0.44
    colgante
    0.43
    llavero
    0.42
     desmotivaciones
    0.42
    brinco
    0.41
    vorschaubild
    0.41
    koszulka
    0.40
    Activations Density 0.021%

    No Known Activations