© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 54925
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "sp"

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

    sp followed by various letters

    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
    yaxis
    -0.52
    lineTo
    -0.49
    userdetails
    -0.47
    RotationOrder
    -0.46
    Contours
    -0.46
    
    -0.45
    queryInterface
    -0.45
    boven
    -0.44
    uxxxx
    -0.44
     Hage
    -0.43
    POSITIVE LOGITS
     Sp
    0.93
     ſp
    0.89
    Sp
    0.89
     sp
    0.85
     SP
    0.82
    SP
    0.82
    sp
    0.76
     Spon
    0.73
     Spart
    0.71
     spu
    0.70
    Activations Density 0.054%

    No Known Activations