Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8091
    Prev
    Next
    INDEX
    Explanations

    technical definitions and programming terms related to data structures and methods

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

    following bracketed abbreviations

    np_acts-logits-general · gemini-2.0-flash

    con or Con

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dignité
    -0.49
    alyptus
    -0.49
    memoized
    -0.48
     eût
    -0.47
    يميديا
    -0.47
     dieux
    -0.47
     JpaRepository
    -0.46
     singoli
    -0.46
     Ashby
    -0.45
     évalu
    -0.45
    POSITIVE LOGITS
     Con
    2.87
    Con
    2.82
     CON
    2.78
    CON
    2.72
    con
    2.70
     con
    2.62
     cons
    2.20
     kon
    2.20
     Cons
    2.15
    Cons
    2.14
    Activations Density 0.640%

    No Known Activations