© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 13584
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and results

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

    References/citations (e.g. @ref42)

    np_acts-logits-general · gemini-2.0-flash

    citations and numbers

    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
     createContext
    -0.53
     OkHttpClient
    -0.52
    ponses
    -0.48
    trice
    -0.48
    HostException
    -0.48
     DevComponents
    -0.46
    Джерела
    -0.46
    produc
    -0.44
     становника
    -0.44
    MENAFN
    -0.44
    POSITIVE LOGITS
    addCriterion
    0.81
    tagHelperRunner
    0.69
     eighty
    0.68
    DockStyle
    0.66
     forty
    0.66
     sixty
    0.65
     fifty
    0.64
     Thirty
    0.64
     seventy
    0.63
    Personendaten
    0.62
    Activations Density 0.661%

    No Known Activations