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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8231
    Prev
    Next
    INDEX
    Explanations

    error messages and issues related to software installation and configuration

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

    Error messages or debugging information

    np_acts-logits-general · gemini-2.0-flash

    build warnings and errors

    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
    ^(@)
    -0.86
    .")
    
    -0.81
    FieldBuilder
    -0.79
    ."));
    -0.78
    Portail
    -0.77
    extAlignment
    -0.76
    ArgsConstructor
    -0.75
    Portale
    -0.75
    !")
    
    -0.74
    enumi
    -0.73
    POSITIVE LOGITS
     [
    0.62
     Warning
    0.61
    Warning
    0.61
     ...
    0.59
     warning
    0.56
     WARNING
    0.56
    warning
    0.55
     <
    0.52
    WARNING
    0.51
    ↵
    0.50
    Activations Density 1.502%

    No Known Activations