Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9055
    Prev
    Next
    INDEX
    Explanations

    occurrences of symbols and formatting in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Спољашње
    -0.66
    agaimana
    -0.64
    CLUYE
    -0.57
    లాలు
    -0.56
     lenker
    -0.55
    Filmografie
    -0.55
     للمعارف
    -0.54
    peteer
    -0.52
    的她
    -0.52
    uests
    -0.52
    POSITIVE LOGITS
    <eos>
    1.55
    </tbody>
    0.91
    ↵↵
    0.88
    ↵↵↵↵
    0.85
    </tr>
    0.85
    "/></
    0.83
    ])))
    0.83
    ↵↵↵↵↵
    0.82
    ↵↵↵
    0.82
    .}
    0.81
    Activations Density 0.577%

    No Known Activations