© 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. 15849
    Prev
    Next
    INDEX
    Explanations

    specific mathematical terms and identities related to advanced mathematical concepts, particularly in areas such as analysis and combinatorics

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

    Tokens preceding mathematical theorems or formulas

    np_acts-logits-general · gemini-2.0-flash

    names of mathematicians and theorems

    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
    fjspx
    -0.63
    CPtr
    -0.61
    insics
    -0.59
     disambiguazione
    -0.58
     nahilalakip
    -0.55
     IndexPath
    -0.53
    ressible
    -0.53
    makeText
    -0.52
    verwijspagina
    -0.51
     otomatig
    -0.51
    POSITIVE LOGITS
    ian
    0.88
    IAN
    0.78
    ův
    0.70
     himself
    0.68
     theorem
    0.67
    iano
    0.63
    ians
    0.63
    iana
    0.62
    esque
    0.60
    –
    0.58
    Activations Density 0.621%

    No Known Activations