© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3414
    Prev
    Next
    INDEX
    Explanations

    references to authors and significant contributors in a given context

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

    Punctuation after a sentence

    np_acts-logits-general · gemini-2.0-flash

    listing items after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.66
     مشين
    -0.55
    ########.
    -0.50
    ssant
    -0.49
    లాలు
    -0.49
    =$?
    -0.48
    setVerticalGroup
    -0.48
     Wiktionnaire
    -0.47
    λίου
    -0.47
    PLEX
    -0.45
    POSITIVE LOGITS
     Parmi
    0.83
     names
    0.76
    names
    0.76
    Parmi
    0.73
    Numerology
    0.72
    Quiénes
    0.69
     Among
    0.69
     nomes
    0.68
     hvem
    0.68
     among
    0.67
    Activations Density 0.327%

    No Known Activations