© 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. 20-GEMMASCOPE-RES-16K
    11. 185
    Prev
    Next
    INDEX
    Explanations

    information related to product offerings and their classifications in various contexts

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

    after "genes" or "stocks"

    np_acts-logits-general · gemini-2.0-flash

    related genes

    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
    perten
    -0.52
     smtplib
    -0.48
     tuong
    -0.47
    beiros
    -0.47
    ethics
    -0.47
     equivalent
    -0.47
    NgModule
    -0.47
    increments
    -0.46
    ynchrotron
    -0.45
    طنين
    -0.45
    POSITIVE LOGITS
     items
    1.06
     titles
    0.88
     projects
    0.83
     Titel
    0.78
    NameInMap
    0.74
    items
    0.72
     item
    0.72
     Items
    0.68
     programs
    0.68
     entries
    0.67
    Activations Density 0.701%

    No Known Activations