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. 1178
    Prev
    Next
    INDEX
    Explanations

    attends to news-related tokens from world-related 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
    2:0.04
    3:0.06
    4:0.00
    5:0.01
    6:0.07
    7:0.08
    8:0.01
    9:0.02
    10:0.01
    11:0.01
    12:0.03
    13:0.32
    14:0.20
    15:0.01
    Negative Logits
     Anſ
    -0.53
     Monfieur
    -0.50
     Houſe
    -0.50
     ſch
    -0.46
     ſont
    -0.44
     ſta
    -0.43
     ainfi
    -0.43
     Perſ
    -0.43
     houſe
    -0.43
     ſche
    -0.42
    POSITIVE LOGITS
     ویکی‌پدی
    0.26
     Numerade
    0.24
    }
    0.23
    ++);
    0.22
     hayan
    0.22
    ]?.
    0.22
    <eos>
    0.22
    re
    0.21
    "")
    0.21
    );
    0.21
    Activations Density 0.233%

    No Known Activations