© 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. 24-GEMMASCOPE-RES-16K
    11. 1783
    Prev
    Next
    INDEX
    Explanations

    code syntax elements, particularly related to control flow and function definitions

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

    Code within try-catch blocks

    np_acts-logits-general · gemini-2.0-flash

    error handling in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dafx
    -0.65
    rungsseite
    -0.65
     queſta
    -0.56
    RenderAtEndOf
    -0.47
     ſtand
    -0.47
    Srin
    -0.47
    ränkt
    -0.44
    oredCriteria
    -0.44
    harusnya
    -0.44
    ⓘ
    -0.44
    POSITIVE LOGITS
    ImageContext
    0.47
    newArrayList
    0.42
     sumpay
    0.38
     abordar
    0.36
     ocze
    0.35
     Stoffe
    0.34
     menghadirkan
    0.34
     conclure
    0.34
     zako
    0.33
     mystère
    0.33
    Activations Density 0.055%

    No Known Activations