© 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. 6049
    Prev
    Next
    INDEX
    Explanations

    code syntax related to error handling in programming

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

    structural syntax and formatting patterns in source code, particularly whitespace, brackets, and colons used in code organization.

    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
    SequentialGroup
    -1.02
    webElementXpaths
    -0.81
     صوتيه
    -0.79
    Personendaten
    -0.76
     surla
    -0.76
     tslint
    -0.74
    Tikang
    -0.73
     فريبيس
    -0.72
     CURIAM
    -0.72
     betweenstory
    -0.71
    POSITIVE LOGITS
    🥹
    0.33
     ২০
    0.28
    replaceAll
    0.28
    🫶
    0.28
    signal
    0.28
     Omicron
    0.27
    🫡
    0.27
    use
    0.27
     might
    0.26
     jakarta
    0.26
    Activations Density 0.125%

    No Known Activations