© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 242
    Prev
    Next
    INDEX
    Explanations

    items related to health and dietary recommendations

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

    Questionnaire/scale items and scores

    np_acts-logits-general · gemini-2.0-flash

    scales and questionnaires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    LookAnd
    -0.75
    rrggbb
    -0.67
     BoxDecoration
    -0.65
    StoryboardSegue
    -0.62
     AssemblyTitle
    -0.61
     BrowserModule
    -0.61
    المناصب
    -0.60
     дописавши
    -0.56
    CppCodeGen
    -0.55
    AddTagHelper
    -0.54
    POSITIVE LOGITS
     scores
    0.47
     score
    0.46
     questionnaire
    0.46
     scoring
    0.45
     scale
    0.40
     questionnaires
    0.40
     scored
    0.39
    score
    0.38
     Questionnaire
    0.37
     scales
    0.36
    Activations Density 0.733%

    No Known Activations