© 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. 22-GEMMASCOPE-RES-16K
    11. 3224
    Prev
    Next
    INDEX
    Explanations

    closing braces, semicolons, and function call endings in code

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

    Code syntax or formatting

    np_acts-logits-general · gemini-2.0-flash

    selection system, first step

    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
    setVerticalGroup
    -0.75
     Roskov
    -0.75
    NameInMap
    -0.74
    MigrationBuilder
    -0.69
    Diweddarwch
    -0.65
    InvalidProtocol
    -0.63
    OGND
    -0.62
    PyTuple
    -0.60
     виправивши
    -0.59
    ();
    -0.58
    POSITIVE LOGITS
    continue
    0.57
     continue
    0.52
     BorderRadius
    0.46
    barbie
    0.44
     prospet
    0.44
    UserScript
    0.43
     financières
    0.43
     continuer
    0.43
     précédents
    0.42
     fortsätter
    0.42
    Activations Density 0.086%

    No Known Activations