© 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. 22-GEMMASCOPE-RES-16K
    11. 889
    Prev
    Next
    INDEX
    Explanations

    error messages related to unsupported media types

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

    Error messages or debugging information

    np_acts-logits-general · gemini-2.0-flash

    string formatting or error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -1.15
     
    -0.99
    <eos>
    -0.93
     I
    -0.90
     R
    -0.89
     A
    -0.86
     He
    -0.85
     M
    -0.84
     V
    -0.82
     P
    -0.81
    POSITIVE LOGITS
     itſelf
    1.67
     myſelf
    1.59
     Monfieur
    1.49
     pleaſure
    1.38
     uſed
    1.31
     raiſ
    1.31
     doubtnut
    1.30
     ་་
    1.30
     ſeveral
    1.27
     Majefty
    1.24
    Activations Density 0.221%

    No Known Activations