© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14876
    Prev
    Next
    INDEX
    Explanations

    complex constructs and concepts related to problem-solving and alternative solutions

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

    that imply difficulty or impossibility

    np_acts-logits-general · gemini-2.0-flash

    how tasks are done

    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
     مشين
    -0.70
     ModelExpression
    -0.68
    ControllerAdvice
    -0.67
    GenerationType
    -0.64
    fromnode
    -0.60
    లాలు
    -0.58
    DebuggerNonUser
    -0.57
    RenderAtEndOf
    -0.57
    干嘛
    -0.57
     occaf
    -0.56
    POSITIVE LOGITS
     adequately
    1.26
     reliably
    1.25
     properly
    1.18
     satisfactorily
    1.18
     successfully
    1.15
     without
    1.12
     safely
    1.11
     efficiently
    1.11
     efficacement
    1.04
     profitably
    1.04
    Activations Density 0.626%

    No Known Activations