Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 116325
    Prev
    Next
    INDEX
    Explanations

    specific verbs and phrases related to recommendations and suggestions in contexts involving health, policy, or societal behaviors

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

    Wikipedia, foreign languages

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     BoxFit
    -0.48
    ThroughAttribute
    -0.47
    awtextra
    -0.46
    isNameExpr
    -0.46
    Atsauces
    -0.45
    Personensuche
    -0.45
    WebElementEntity
    -0.44
     Turquía
    -0.44
    richTextPanel
    -0.44
     Paglinawan
    -0.44
    POSITIVE LOGITS
     Olympedia
    0.46
    Сылтамалар
    0.40
     ویکی‌پدی
    0.38
     Staple
    0.37
    ruptedException
    0.37
     gyhoeddwyd
    0.36
    اح
    0.35
    нія
    0.35
    Rab
    0.35
     Ver
    0.34
    Activations Density 0.095%

    No Known Activations