© 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. 17-GEMMASCOPE-RES-16K
    6. 8792
    Prev
    Next
    INDEX
    Explanations

    phrases that express skepticism or challenge the validity of assertions or evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réflexion
    -0.54
     ***/
    -0.51
    BibitemShut
    -0.50
    sedown
    -0.50
    atimes
    -0.48
     ſtand
    -0.48
    ̓
    -0.48
     ſche
    -0.47
    )')
    -0.47
    "}")
    -0.47
    POSITIVE LOGITS
     validity
    1.52
    validity
    1.25
     effectiveness
    1.24
     appropriateness
    1.17
     suitability
    1.14
     viability
    1.13
     efficacy
    1.12
     legitimacy
    1.12
     adequacy
    1.12
     veracity
    1.12
    Activations Density 0.763%

    No Known Activations