© 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 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. 14689
    Prev
    Next
    INDEX
    Explanations

    elements related to technical instructions or commands in a computing context

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

    Followed by French words

    np_acts-logits-general · gemini-2.0-flash

    ca tape sur les nerf

    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
    ſelf
    -0.68
    styleType
    -0.64
    migrationBuilder
    -0.64
    _-_
    -0.64
    .";
    -0.64
    SPJ
    -0.63
     itſelf
    -0.62
     egli
    -0.62
    ])));
    -0.62
     ¦
    -0.60
    POSITIVE LOGITS
     fucked
    0.64
     thing
    0.63
     things
    0.62
     shit
    0.62
     crazy
    0.60
     horrible
    0.59
     haha
    0.58
     saying
    0.58
    crazy
    0.56
     bullshit
    0.56
    Activations Density 0.183%

    No Known Activations