© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K__L0-22
    11. 708
    Prev
    Next
    INDEX
    Explanations

    first-person perspectives and personal narratives.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @gulkoa

    mathematical and technical terms or expressions.

    oai_token-act-pair · gpt-4oTriggered by @gulkoa

    proper nouns and specialized terms across various contexts like names, technical jargon, and mathematical symbols.

    oai_token-act-pair · deepseek-r1Triggered by @gulkoa
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.83
    <eos>
    -0.37
    ↵↵
    -0.33
    </tr>
    -0.32
    ’
    -0.31
    </i>
    -0.31
    </b>
    -0.30
    р
    -0.30
    ро
    -0.29
    fo
    -0.29
    POSITIVE LOGITS
     Efq
    0.60
     myſelf
    0.57
     Monfieur
    0.56
     ſeveral
    0.56
     purpoſe
    0.56
     Majefty
    0.55
     Jefus
    0.54
     themſelves
    0.52
     pleaſure
    0.52
     itſelf
    0.51
    Activations Density 42.824%

    No Known Activations