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. 1258
    Prev
    Next
    INDEX
    Explanations

    attends to table row tokens from less significant tags

    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
    2:0.01
    3:0.01
    4:0.01
    5:0.01
    6:0.65
    7:0.02
    8:0.01
    9:0.01
    10:0.05
    11:0.01
    12:0.01
    13:0.01
    14:0.04
    15:0.04
    Negative Logits
    ");
    -0.51
    }}}
    -0.50
    </
    -0.47
    })}
    -0.47
    }}
    -0.46
    "))
    -0.46
    }"
    -0.46
    }
    -0.46
    }",
    -0.46
    });
    -0.46
    POSITIVE LOGITS
     miniaturka
    0.63
     informée
    0.60
     ainfi
    0.59
     desmotivaciones
    0.59
     queſta
    0.58
     abstrato
    0.57
     feroit
    0.56
    pulseira
    0.56
    writeFieldEnd
    0.56
    ésultats
    0.55
    Activations Density 0.011%

    No Known Activations