© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13529
    Prev
    Next
    INDEX
    Explanations

    time and date formatting specifications

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

    Formatting symbols or characters

    np_acts-logits-general · gemini-2.0-flash

    date and number formatting

    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
     minOccurs
    -0.67
     >=",
    -0.60
    MemoryWarning
    -0.57
    migrationBuilder
    -0.56
     Bingham
    -0.53
    openqa
    -0.51
    WritableDatabase
    -0.51
    EClass
    -0.49
     étudier
    -0.49
    obium
    -0.48
    POSITIVE LOGITS
     format
    1.05
     formatter
    1.04
     formatting
    1.02
    format
    0.97
     Format
    0.96
     fmt
    0.95
     formats
    0.94
    Formatter
    0.93
    formatter
    0.93
     FORMAT
    0.90
    Activations Density 0.265%

    No Known Activations