© 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. 6410
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements in programming languages

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

    whitespace and newline characters in 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
     Roskov
    -0.48
    formik
    -0.43
     considérons
    -0.41
    +:+
    -0.39
     يتيمه
    -0.37
     intptr
    -0.36
    請繼續往下閱讀
    -0.35
     Signalez
    -0.35
    ParallelGroup
    -0.35
    jsxFileName
    -0.34
    POSITIVE LOGITS
    exitRule
    0.61
    </em>
    0.56
    IsMutable
    0.52
    </i>
    0.52
    NameInMap
    0.50
    EndProject
    0.49
    </blockquote>
    0.48
    })*/
    0.48
     $_[
    0.48
    ();*/
    0.48
    Activations Density 0.579%

    No Known Activations