© 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. 10653
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and function definitions

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

    Code or data snippets

    np_acts-logits-general · gemini-2.0-flash

    after a keyword

    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
    GraphicsUnit
    -0.57
    AddTagHelper
    -0.50
    WriteTagHelper
    -0.50
    rrggbb
    -0.49
    
    -0.46
    RTDA
    -0.45
     transfieras
    -0.43
    OCCURRED
    -0.42
    andExpect
    -0.41
     getColumn
    -0.41
    POSITIVE LOGITS
     jälkeen
    0.46
    دانشنامهٔ
    0.42
     ErrIntOverflow
    0.41
     FetchType
    0.41
     parlak
    0.39
    Gruß
    0.39
     curiosa
    0.39
    Pautan
    0.37
    Colorful
    0.37
    CodedInputStream
    0.37
    Activations Density 0.156%

    No Known Activations