© 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. 8306
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and data structures

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

    Tokens after specific capitalized words

    np_acts-logits-general · gemini-2.0-flash

    plural nouns forming compounds

    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
    ty
    -0.76
    tra
    -0.72
    t
    -0.69
    tal
    -0.67
    the
    -0.67
    em
    -0.66
     AspNetCore
    -0.64
    tk
    -0.63
    so
    -0.63
    sub
    -0.63
    POSITIVE LOGITS
    Jaunes
    0.81
     Taktlose
    0.74
     LCCN
    0.73
     Egli
    0.72
     réglable
    0.72
    adaptiveStyles
    0.71
    hips
    0.69
     дописавши
    0.69
    namefont
    0.67
     nélk
    0.67
    Activations Density 1.446%

    No Known Activations