© 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. 4557
    Prev
    Next
    INDEX
    Explanations

    occurrences of file-related keywords or concepts

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

    Text after single letters

    np_acts-logits-general · gemini-2.0-flash

    F or f followed by specific punctuation or words

    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
     מוכ
    -0.45
    assertThat
    -0.42
    ánchez
    -0.41
    withIdentifier
    -0.40
    клопе
    -0.40
    bootstrapcdn
    -0.40
     mor
    -0.39
    TintMode
    -0.39
     đỡ
    -0.38
    DispatchToProps
    -0.38
    POSITIVE LOGITS
    ttemberg
    0.73
    تفصیلات
    0.71
     doInBackground
    0.68
     Italijani
    0.67
     للاسماء
    0.66
     كومونز
    0.66
    lossians
    0.64
     HasFactory
    0.64
    RegressionTest
    0.63
     détruit
    0.63
    Activations Density 0.245%

    No Known Activations