© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16301
    Prev
    Next
    INDEX
    Explanations

    the substring "sp" in various forms within technical or programming contexts

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

    sp, spN, spI, sps

    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
    uxxxx
    -0.51
    rawDesc
    -0.45
     Gegenteil
    -0.45
    queryInterface
    -0.45
     Schwier
    -0.45
    __":
    -0.45
    yaxis
    -0.45
    setVerticalGroup
    -0.44
    thâu
    -0.43
    SourceChecksum
    -0.42
    POSITIVE LOGITS
    sp
    2.44
     sp
    1.96
    SP
    1.65
     Sp
    1.50
    Sp
    1.48
     SP
    1.45
    sps
    1.17
     ſp
    1.09
    spar
    1.00
    spk
    0.98
    Activations Density 0.016%

    No Known Activations