© 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. 9-GEMMASCOPE-RES-131K
    11. 14013
    Prev
    Next
    INDEX
    Explanations

    references to sequencing or genomic technologies, particularly involving the term "GS."

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

    GS FLX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IconButton
    -0.44
     IconButton
    -0.41
    teh
    -0.40
     vegetarian
    -0.40
     Harn
    -0.40
     controlling
    -0.39
     Noyes
    -0.39
    Enllaços
    -0.39
    argout
    -0.39
     useParams
    -0.39
    POSITIVE LOGITS
     GS
    2.05
    GS
    1.82
     gs
    1.44
     Gs
    1.09
     GSA
    1.01
     gsx
    1.00
    gs
    0.86
     GSC
    0.86
    Gs
    0.86
     GSP
    0.79
    Activations Density 0.010%

    No Known Activations