© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10632
    Prev
    Next
    INDEX
    Explanations

    elements and keywords related to programming, especially imports and data structures

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

    Imports in code

    np_acts-logits-general · gemini-2.0-flash

    code import statements

    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
     Administrativna
    -0.70
     Paglinawan
    -0.68
    ьаж
    -0.49
    ⟬
    -0.49
     nakalista
    -0.48
    TargetException
    -0.47
     lateinit
    -0.46
    iettivo
    -0.46
    Referencie
    -0.45
    ftagPool
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.46
    addCriterion
    0.42
    PreferredItem
    0.39
    BeginContext
    0.39
    LookAnd
    0.38
     tigre
    0.36
    enumii
    0.35
     HttpNotFound
    0.35
    GraphicsUnit
    0.35
    TableAdapter
    0.35
    Activations Density 0.461%

    No Known Activations