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. 1187
    Prev
    Next
    INDEX
    Explanations

    attends to the numeral "1" from various scientific and statistical contexts

    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
    1:0.03
    2:0.04
    3:0.03
    4:0.01
    5:0.05
    6:0.02
    7:0.43
    8:0.02
    9:0.02
    10:0.02
    11:0.06
    12:0.06
    13:0.07
    14:0.02
    15:0.01
    Negative Logits
    2
    -0.98
    1
    -0.60
    5
    -0.56
    3
    -0.56
    4
    -0.52
    6
    -0.51
    7
    -0.50
    8
    -0.47
    0
    -0.46
    9
    -0.44
    POSITIVE LOGITS
    <unused79>
    1.46
    <unused41>
    1.46
    <unused8>
    1.46
    <pad>
    1.45
    <unused28>
    1.45
    <unused14>
    1.45
    <unused23>
    1.45
    <unused16>
    1.45
    [@BOS@]
    1.45
    <unused3>
    1.45
    Activations Density 0.162%

    No Known Activations