© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3649
    Prev
    Next
    INDEX
    Explanations

    references to data storage and handling in a programming context

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

    Code-related tokens or file paths

    np_acts-logits-general · gemini-2.0-flash

    bits.module, row['key'], Data[key], cfg.key, POST['key']

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    timewa
    -0.47
    ())->
    -0.45
    ))->
    -0.41
    zeß
    -0.41
    ())),
    -0.40
    "]();
    -0.40
     {}
    -0.39
    ')),
    -0.39
    })=
    -0.38
     judiciaire
    -0.38
    POSITIVE LOGITS
     المعيارى
    0.97
    CppCodeGen
    0.86
     Roskov
    0.84
    يكب
    0.83
    ThroughAttribute
    0.83
    databind
    0.82
    LLocation
    0.81
    WireFormatLite
    0.76
     فريبيس
    0.75
    SBATCH
    0.73
    Activations Density 0.069%

    No Known Activations