© 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. 15173
    Prev
    Next
    INDEX
    Explanations

    instances of the word "evidence" and related terms, indicating a focus on scientific proof or data

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

    Statements about "evidence"

    np_acts-logits-general · gemini-2.0-flash

    evidence supporting or suggesting

    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
    uxxxx
    -0.68
    BarStyle
    -0.66
    expandindo
    -0.66
    verifyException
    -0.66
    ourable
    -0.64
     Normdatei
    -0.62
    Με
    -0.62
     useRouter
    -0.62
    🏻
    -0.61
     Audiodateien
    -0.61
    POSITIVE LOGITS
     Evidence
    0.68
    Evidence
    0.65
    evidence
    0.63
    Personensuche
    0.60
     evidence
    0.60
     EVIDENCE
    0.58
     Evid
    0.58
     evidences
    0.52
     tampering
    0.51
    Suggest
    0.51
    Activations Density 0.221%

    No Known Activations