© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14991
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and class definitions in code snippets

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

    numbers and digits in code and technical documentation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.59
    writeFieldEnd
    -0.55
    MLLoader
    -0.55
    MigrationBuilder
    -0.54
    AxisAlignment
    -0.53
    HasBeenSet
    -0.51
     Италијани
    -0.51
    PerformLayout
    -0.51
    CppMethod
    -0.49
    SourceChecksum
    -0.49
    POSITIVE LOGITS
     feroit
    0.58
    hæng
    0.56
     romántico
    0.55
     flotante
    0.53
     Usaha
    0.52
     suyo
    0.52
     vocales
    0.51
     Monfieur
    0.50
    devším
    0.50
     conmigo
    0.49
    Activations Density 0.437%

    No Known Activations