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. 1318
    Prev
    Next
    INDEX
    Explanations

    attends to "solve" tokens from combinatorial expressions or mathematical statements

    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
    0:0.38
    1:0.03
    2:0.01
    3:0.02
    4:0.03
    5:0.04
    6:0.03
    7:0.03
    8:0.04
    9:0.05
    10:0.07
    11:0.06
    12:0.06
    13:0.04
    14:0.01
    15:0.02
    Negative Logits
     
    -0.50
    .
    -0.47
     the
    -0.47
    ,
    -0.44
    -
    -0.42
     in
    -0.41
     (
    -0.41
     to
    -0.39
     a
    -0.39
     de
    -0.34
    POSITIVE LOGITS
    .)}
    0.66
    })*/
    0.65
    )*/
    0.62
    }))
    
    0.60
    ]")]
    0.60
    });*/
    0.60
     ब्रेकडाउन
    0.59
    };*/
    0.59
     */
    
    
    0.59
    ")}
    0.57
    Activations Density 0.196%

    No Known Activations