Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 6073
    Prev
    Next
    INDEX
    Explanations

    attends to tokens indicating a state or action in the present from tokens indicating a supportive or additional context

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 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
    0:0.04
    1:0.09
    2:0.14
    3:0.09
    4:0.11
    5:0.18
    6:0.17
    7:0.14
    Negative Logits
     feroit
    -0.70
     auroit
    -0.68
     eût
    -0.68
     ainfi
    -0.67
     étoit
    -0.67
     quelcon
    -0.66
     réaliste
    -0.66
     noires
    -0.65
     traditionnels
    -0.65
     culturelles
    -0.64
    POSITIVE LOGITS
    ++$
    0.44
     Des
    0.44
    ]$}
    0.40
     des
    0.40
    ]>=
    0.40
    #}
    0.39
     trans
    0.37
     ré
    0.37
    "})
    0.36
     dé
    0.36
    Activations Density 0.048%

    No Known Activations