© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1365
    Prev
    Next
    INDEX
    Explanations

    assertions and denials regarding statements or beliefs

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

    "Not saying" or equivalent phrases

    np_acts-logits-general · gemini-2.0-flash

    qualifying statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.56
    ervare
    -0.48
     hasNext
    -0.48
    คง
    -0.46
    :+:
    -0.46
    
    -0.46
     jPanel
    -0.46
    DispatchToProps
    -0.46
    moveToNext
    -0.44
    ต่อ
    -0.44
    POSITIVE LOGITS
     necessarily
    0.72
     leſs
    0.65
     necessariamente
    0.60
     lesser
    0.60
     necesariamente
    0.58
    necessarily
    0.57
     Roumanie
    0.56
     quelconque
    0.56
    Cartney
    0.55
     inferiority
    0.55
    Activations Density 0.216%

    No Known Activations