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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4184
    Prev
    Next
    INDEX
    Explanations

    control commands or instructions within a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after colons or underscores

    np_acts-logits-general · gemini-2.0-flash

    technical, archaic, diverse scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.60
    </strong>
    -0.57
     com
    -0.48
    !
    -0.47
     fin
    -0.45
     doi
    -0.43
     zap
    -0.43
     p
    -0.42
    ”
    -0.42
     b
    -0.42
    POSITIVE LOGITS
     Efq
    1.16
     Monfieur
    0.98
    ſelf
    0.91
     myſelf
    0.90
     Jefus
    0.88
    хьтан
    0.86
     ErrIntOverflow
    0.86
     Shakspeare
    0.85
    AxisAlignment
    0.85
     itſelf
    0.83
    Activations Density 0.286%

    No Known Activations