© 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. 9696
    Prev
    Next
    INDEX
    Explanations

    elements and concepts related to Python's naming conventions and module management

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

    Double underscores, surrounding or at the beginning of words

    np_acts-logits-general · gemini-2.0-flash

    Python dunder names

    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
     autorytatywna
    -0.84
     GenerationType
    -0.80
     HasFactory
    -0.80
    principalTable
    -0.80
    RegistryLite
    -0.76
    parsedMessage
    -0.75
    httphttps
    -0.75
    enderror
    -0.74
     Signalez
    -0.73
    Personensuche
    -0.73
    POSITIVE LOGITS
     hidden
    0.46
     special
    0.41
    hidden
    0.41
    Hidden
    0.41
    ↵↵
    0.40
    qu
    0.37
    ↵
    0.37
    sil
    0.35
    special
    0.35
     sil
    0.35
    Activations Density 0.627%

    No Known Activations