© 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. 18-GEMMASCOPE-RES-16K
    11. 8882
    Prev
    Next
    INDEX
    Explanations

    phrases that express certainty or assurance

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

    "sure" and its variants

    np_acts-logits-general · gemini-2.0-flash

    sure followed by confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Obrador
    -0.63
    ArrowToggle
    -0.59
    ethnicity
    -0.56
    audiovisuel
    -0.55
     Fielding
    -0.53
    odeficiency
    -0.52
    ppp
    -0.52
    uitton
    -0.50
    FFIX
    -0.50
    middot
    -0.49
    POSITIVE LOGITS
    footed
    0.78
    tainty
    0.78
     chắn
    0.77
    fire
    0.75
     footed
    0.74
     Uncertain
    0.71
    makeConstraints
    0.68
     "'");
    0.68
     siebie
    0.64
    PropertyChanging
    0.64
    Activations Density 0.101%

    No Known Activations