© 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. 93068
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 's' in various contexts

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

    mathematical or code variable s

    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
     rodilla
    -0.56
     bakgrund
    -0.51
     måtte
    -0.51
    الحياه
    -0.50
     föränd
    -0.50
    躇
    -0.49
    ParallelGroup
    -0.49
    Slf
    -0.49
    PageRoute
    -0.48
     BrowserModule
    -0.48
    POSITIVE LOGITS
    S
    1.01
     S
    0.98
     s
    0.96
    getS
    0.89
    s
    0.81
    Ss
    0.77
     SBS
    0.77
     getS
    0.75
    sS
    0.75
     SSS
    0.73
    Activations Density 0.181%

    No Known Activations