© 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. 13904
    Prev
    Next
    INDEX
    Explanations

    terms related to entities and their classifications within a fictional universe

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

    Word fragments/endings

    np_acts-logits-general · gemini-2.0-flash

    elemental, break, form, bomb, shield

    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
     engraçadas
    -0.70
     femininas
    -0.68
     brancas
    -0.60
     démocr
    -0.59
     femininos
    -0.59
     vermelhas
    -0.58
     parteci
    -0.56
     felizes
    -0.56
     VizieR
    -0.55
     partito
    -0.54
    POSITIVE LOGITS
    /*
    0.57
    fang
    0.55
     Walker
    0.54
     Drake
    0.52
    mancy
    0.50
    Drake
    0.50
     Lord
    0.50
    folk
    0.50
     energy
    0.49
    born
    0.48
    Activations Density 0.424%

    No Known Activations