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. 1185
    Prev
    Next
    INDEX
    Explanations

    attends to "getElementById" from any occurrences of "swift" in the sequence

    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
    1:0.02
    2:0.58
    3:0.03
    4:0.01
    5:0.01
    6:0.03
    7:0.02
    8:0.01
    9:0.01
    10:0.02
    11:0.01
    12:0.02
    13:0.06
    14:0.08
    15:0.01
    Negative Logits
     ſta
    -0.56
     ſte
    -0.52
     pleaſure
    -0.51
     faſt
    -0.50
     ſche
    -0.47
     ſtre
    -0.46
     deſt
    -0.45
     ſch
    -0.44
     fubject
    -0.44
     myſelf
    -0.44
    POSITIVE LOGITS
    hi
    0.42
    this
    0.41
    ep
    0.41
    clear
    0.40
    red
    0.40
    ign
    0.40
    get
    0.40
    let
    0.39
    ha
    0.39
    en
    0.39
    Activations Density 0.021%

    No Known Activations