© 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. 20-GEMMASCOPE-RES-16K
    11. 7147
    Prev
    Next
    INDEX
    Explanations

    content related to discussions or opinions about strategies and decisions

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

    Follows a question or statement

    np_acts-logits-general · gemini-2.0-flash

    basically, essentially, what

    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
     تضيفلها
    -0.65
    tagHelperRunner
    -0.60
     विश्वसनीयता
    -0.58
    endwhile
    -0.58
     betweenstory
    -0.57
    CloseOperation
    -0.56
    SharedModule
    -0.56
    كذا
    -0.54
    ModelSerializer
    -0.54
    LookAnd
    -0.54
    POSITIVE LOGITS
     what
    1.28
    what
    0.99
    What
    0.92
     essentially
    0.89
     What
    0.86
     basically
    0.86
    Basically
    0.82
     Essentially
    0.81
    essentially
    0.80
     Basically
    0.80
    Activations Density 0.424%

    No Known Activations