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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11365
    Prev
    Next
    INDEX
    Explanations

    lines of code related to file operations and error handling

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

    File operations and error streams

    np_acts-logits-general · gemini-2.0-flash

    ,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.62
    izr
    -0.58
    chymal
    -0.52
    AnchorStyles
    -0.52
     continúas
    -0.51
     Langer
    -0.50
    hanger
    -0.50
    /**
    -0.48
    DMETHOD
    -0.48
    ulsi
    -0.48
    POSITIVE LOGITS
     stream
    0.97
     streams
    0.90
    stream
    0.89
     Stream
    0.85
     fopen
    0.84
    Stream
    0.82
     opened
    0.80
     Streams
    0.78
     FileInputStream
    0.77
    streams
    0.77
    Activations Density 0.332%

    No Known Activations