© 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. 20-GEMMASCOPE-RES-16K
    11. 1149
    Prev
    Next
    INDEX
    Explanations

    programming code structures and comments

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    code comments and programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.86
    TagMode
    -0.74
    saraba
    -0.73
     saites
    -0.67
    AlterField
    -0.63
    Hochspringen
    -0.63
    +#+#
    -0.62
    GraphicsUnit
    -0.60
     useHistory
    -0.60
    SequentialGroup
    -0.59
    POSITIVE LOGITS
     ModelExpression
    0.72
    enderror
    0.71
    LookAnd
    0.59
     الاطلاع
    0.55
    \]
    0.52
    :])
    0.52
    </tfoot>
    0.51
    ])
    0.51
    WEBPACK
    0.50
    ]),
    0.49
    Activations Density 0.062%

    No Known Activations