© 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. 20-GEMMASCOPE-RES-16K
    11. 15884
    Prev
    Next
    INDEX
    Explanations

    statements of acknowledgment or admission regarding actions or events

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

    Statements of acknowledgement or confession

    np_acts-logits-general · gemini-2.0-flash

    stating admissions or claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.56
     exhortation
    -0.53
     समीक्षाओं
    -0.52
    ValueStyle
    -0.48
     argumenta
    -0.47
    értel
    -0.46
    definitions
    -0.46
    BufferException
    -0.46
    ftagPool
    -0.46
    TacToe
    -0.45
    POSITIVE LOGITS
     intention
    0.85
     intentions
    0.82
    自己是
    0.76
     publicly
    0.75
     aloud
    0.74
     Absicht
    0.70
     wanting
    0.69
     auprès
    0.68
     being
    0.68
     intent
    0.67
    Activations Density 0.423%

    No Known Activations