© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2612
    Prev
    Next
    INDEX
    Explanations

    patterns of special characters and specific formatting in technical text

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

    "sp" followed by other characters/symbols

    np_acts-logits-general · gemini-2.0-flash

    sp² and sp³ bonding

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ClientRect
    -0.52
     Touchable
    -0.45
    jTable
    -0.44
     Infórmanos
    -0.40
    queryInterface
    -0.39
    uxxxx
    -0.39
    userdetails
    -0.39
     Referential
    -0.38
     BaseModel
    -0.37
    Notae
    -0.37
    POSITIVE LOGITS
     Sp
    1.30
     sp
    1.27
    Sp
    1.26
    sp
    1.15
     SP
    1.14
     Spa
    1.07
     Spalding
    1.07
    SP
    1.07
    Spa
    1.06
     spa
    1.05
    Activations Density 0.214%

    No Known Activations