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. 1365
    Prev
    Next
    INDEX
    Explanations

    attends to the closing token "endif" from opening comment tokens

    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
    1:0.01
    2:0.07
    3:0.06
    4:0.02
    5:0.01
    6:0.11
    7:0.09
    8:0.02
    9:0.01
    10:0.03
    11:0.02
    12:0.06
    13:0.24
    14:0.11
    15:0.03
    Negative Logits
     Italij
    -0.51
     zijne
    -0.50
    OGND
    -0.50
    parsedMessage
    -0.48
     dezelve
    -0.47
     mijne
    -0.46
    enderror
    -0.44
     للمعارف
    -0.44
     navideño
    -0.42
     avoient
    -0.40
    POSITIVE LOGITS
    <eos>
    0.60
     Con
    0.48
     Che
    0.47
     Fac
    0.47
     A
    0.47
     a
    0.47
     fac
    0.47
     ‘
    0.46
     e
    0.45
     Tim
    0.45
    Activations Density 0.021%

    No Known Activations