© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42047
    Prev
    Next
    INDEX
    Explanations

    class and variable definitions in programming code

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

    code structure delimiters

    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
    +:+
    -0.65
     vectorielle
    -0.62
     betweenstory
    -0.56
    SerializedSize
    -0.55
     nahilalakip
    -0.54
    transQ
    -0.54
     vettor
    -0.52
    Datuak
    -0.52
    StoreMessageInfo
    -0.52
    AddTagHelper
    -0.51
    POSITIVE LOGITS
    ist
    0.40
    〈
    0.40
    だけの
    0.40
     censiti
    0.40
     Ade
    0.38
    ☉
    0.37
    ade
    0.36
    proba
    0.36
    nom
    0.36
     Container
    0.36
    Activations Density 0.021%

    No Known Activations