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. 1205
    Prev
    Next
    INDEX
    Explanations

    attends to initialization or definition tokens from callbacks or response tokens

    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
    0:0.07
    1:0.01
    2:0.01
    3:0.02
    4:0.02
    5:0.01
    6:0.05
    7:0.07
    8:0.01
    9:0.01
    10:0.01
    11:0.02
    12:0.14
    13:0.01
    14:0.04
    15:0.43
    Negative Logits
     and
    -0.54
    ),
    -0.48
    )
    -0.47
    ).
    -0.43
    ));
    -0.40
    ]),
    -0.40
    }
    -0.39
    )),
    -0.39
    );
    -0.38
    ]
    -0.37
    POSITIVE LOGITS
    <unused43>
    1.41
    <pad>
    1.41
    <unused8>
    1.41
    <unused17>
    1.41
    <unused68>
    1.41
    <unused74>
    1.41
    <unused42>
    1.41
    <unused41>
    1.41
    <unused23>
    1.41
    <unused28>
    1.41
    Activations Density 0.009%

    No Known Activations