© 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. 24-GEMMASCOPE-RES-16K
    11. 2592
    Prev
    Next
    INDEX
    Explanations

    references to specific scholarly citations or authors in scientific literature

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

    Followed by "al" after "et"

    np_acts-logits-general · gemini-2.0-flash

    et al. citations

    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
    WithIOException
    -0.77
    addCriterion
    -0.77
    enterOuterAlt
    -0.74
    InstrumentedTest
    -0.69
    ⓧ
    -0.65
     EClass
    -0.65
    Personendaten
    -0.61
    sizeCache
    -0.61
    ista
    -0.60
     InputDecoration
    -0.59
    POSITIVE LOGITS
     al
    0.87
     vermelhas
    0.49
     pauvreté
    0.49
     ál
    0.48
     adicionais
    0.48
     alia
    0.47
     stället
    0.47
     moglie
    0.46
     brancas
    0.46
     cetera
    0.46
    Activations Density 0.079%

    No Known Activations