© 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. 18-GEMMASCOPE-RES-16K
    11. 8857
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and data structures

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

    C++ code snippets

    np_acts-logits-general · gemini-2.0-flash

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Brainz
    -0.69
     HasFactory
    -0.66
    AccessorTable
    -0.65
     Italijanski
    -0.63
    complexContent
    -0.62
     eventdata
    -0.62
    InitVars
    -0.61
    dersfield
    -0.60
     Walkover
    -0.59
     ligiloj
    -0.59
    POSITIVE LOGITS
     auto
    0.58
    auto
    0.52
    ))).
    0.51
     BorderRadius
    0.49
    ölker
    0.48
     авто
    0.46
    moveToFirst
    0.45
     Auto
    0.45
     sopra
    0.43
    gent
    0.43
    Activations Density 0.161%

    No Known Activations