© 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. 2959
    Prev
    Next
    INDEX
    Explanations

    programming-related structures and identifiers, specifically those related to data handling and validation

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

    Code snippets with brackets and environment variables

    np_acts-logits-general · gemini-2.0-flash

    environment variables

    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
     дописавши
    -0.77
     للمعارف
    -0.70
    MessageTagHelper
    -0.66
    tagHelper
    -0.65
    DataAnnotations
    -0.64
     المعيارى
    -0.62
     nahilalakip
    -0.60
     متعلقه
    -0.59
    ReusableCell
    -0.58
    NamedQueries
    -0.57
    POSITIVE LOGITS
    Viited
    0.49
     kurios
    0.49
     chimiques
    0.48
     spirituale
    0.45
    Revenir
    0.45
     ää
    0.45
     CURIAM
    0.44
     Friedens
    0.44
    Alpha
    0.43
     couverte
    0.43
    Activations Density 0.162%

    No Known Activations