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

    Neuronpedia

    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. 15764
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures or algorithms in programming

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

    numeric values and constants in technical documentation and code.

    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
    {}/
    -0.43
    jší
    -0.42
    IActionResult
    -0.39
     ?',
    -0.39
    Vanjske
    -0.39
    Composable
    -0.38
    SqlClient
    -0.38
    Σε
    -0.37
     Hombre
    -0.37
    ToAction
    -0.37
    POSITIVE LOGITS
    8
    1.05
    Билгалдахарш
    0.67
     huit
    0.59
     Савезне
    0.58
     EIGHT
    0.58
     eighth
    0.57
     Eight
    0.56
    AutoScaleMode
    0.56
     delapan
    0.56
     Eighty
    0.55
    Activations Density 0.988%

    No Known Activations