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-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 378
    Prev
    Next
    INDEX
    Explanations

    attends to code-related tokens enclosed in the code tags from any later tokens

    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
    0:0.05
    1:0.02
    2:0.03
    3:0.03
    4:0.70
    5:0.05
    6:0.04
    7:0.05
    Negative Logits
    }}}{\
    -0.48
    </caption>
    -0.47
    })}
    -0.46
    )​
    -0.46
    )}</
    -0.46
    AppMethodBeat
    -0.45
    )__
    -0.45
    </em>
    -0.45
    }}}\
    -0.44
     ligiloj
    -0.44
    POSITIVE LOGITS
    ^(@)
    0.40
     téléph
    0.35
     adicionais
    0.32
     further
    0.32
     deschis
    0.32
     payé
    0.31
     רבה
    0.30
     supplémentaires
    0.30
     later
    0.30
    Dienst
    0.30
    Activations Density 0.009%

    No Known Activations