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. 1332
    Prev
    Next
    INDEX
    Explanations

    attends to the token "going" from various contexts, while also looking for corresponding "going" tokens that indicate future actions or plans

    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
    0:0.03
    1:0.04
    2:0.02
    3:0.11
    4:0.34
    5:0.07
    6:0.04
    7:0.06
    8:0.04
    9:0.02
    10:0.02
    11:0.04
    12:0.04
    13:0.03
    14:0.03
    15:0.01
    Negative Logits
     wasn
    -0.56
     didn
    -0.53
     wouldn
    -0.51
     doesn
    -0.49
     don
    -0.48
    -0.48
     shouldn
    -0.47
     just
    -0.47
     went
    -0.46
     isn
    -0.46
    POSITIVE LOGITS
     ainfi
    1.00
     Houſe
    0.96
    ſelf
    0.90
     queſta
    0.90
     myſelf
    0.88
     houſe
    0.87
     Anſ
    0.86
     Monfieur
    0.85
     pleaſure
    0.85
     ſche
    0.84
    Activations Density 0.079%

    No Known Activations