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. 1262
    Prev
    Next
    INDEX
    Explanations

    attends to the token "clang" from the token "defined" in debugging contexts

    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
    2:0.03
    3:0.04
    4:0.02
    5:0.01
    6:0.06
    7:0.09
    8:0.01
    9:0.02
    10:0.01
    11:0.04
    12:0.38
    13:0.03
    14:0.11
    15:0.04
    Negative Logits
    )"),
    -0.90
    "]);
    
    -0.88
    ]));
    
    -0.88
     desmotivaciones
    -0.86
    ]),
    
    -0.85
    ')))
    -0.85
    '}),
    -0.84
    }),
    
    -0.84
    ']))
    
    -0.83
    "]))
    -0.83
    POSITIVE LOGITS
     a
    0.54
     and
    0.51
     
    0.50
     the
    0.49
     H
    0.49
    ,
    0.47
     of
    0.47
     on
    0.46
     V
    0.45
     in
    0.44
    Activations Density 0.005%

    No Known Activations