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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11030
    Prev
    Next
    INDEX
    Explanations

    elements related to selection and choice

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

    following prepositions

    np_acts-logits-general · gemini-2.0-flash

    or to

    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
     okuyayım
    -0.53
    Vidite
    -0.50
    省市镇
    -0.49
    RuleContext
    -0.49
    AxisAlignment
    -0.49
    expandindo
    -0.47
    FunctionFlags
    -0.47
     Italijanski
    -0.47
    addCriterion
    -0.47
    openzeppelin
    -0.45
    POSITIVE LOGITS
    それとも
    0.44
    queryInterface
    0.41
    ulipas
    0.41
     oppure
    0.38
     незавершена
    0.38
     virtuales
    0.37
    最快更新
    0.37
    rrggbb
    0.37
     yourself
    0.35
     felici
    0.33
    Activations Density 0.403%

    No Known Activations