© 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. 28-GEMMASCOPE-RES-16K
    11. 3596
    Prev
    Next
    INDEX
    Explanations

    statements related to error handling and conditional checks in programming code

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

    Followed by tracing, swag, or err in the code

    np_acts-logits-general · gemini-2.0-flash

    conditional code checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     au
    -0.34
    son
    -0.32
     un
    -0.31
     Remember
    -0.31
    IBIL
    -0.30
     Kranken
    -0.30
     safe
    -0.30
    انیا
    -0.29
     needn
    -0.29
    Alina
    -0.29
    POSITIVE LOGITS
    httphttps
    0.91
    Diweddarwch
    0.79
    hoeddwyd
    0.77
    FunctionFlags
    0.75
     насељу
    0.69
     cherchés
    0.68
    ArgsConstructor
    0.68
    ThroughAttribute
    0.67
    migrationBuilder
    0.66
    GTCX
    0.66
    Activations Density 0.085%

    No Known Activations