© 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. 16-GEMMASCOPE-RES-16K
    11. 1274
    Prev
    Next
    INDEX
    Explanations

    references to letters or symbols in text

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

    the word "letter"

    np_acts-logits-general · gemini-2.0-flash

    letters picked

    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
    mylist
    -0.59
    Lähteet
    -0.59
    ModelAdmin
    -0.59
    makeConstraints
    -0.58
    ريكي
    -0.56
    ganggu
    -0.54
    amını
    -0.53
    foria
    -0.53
    сылкі
    -0.53
     Kun
    -0.52
    POSITIVE LOGITS
     letters
    1.79
     Letters
    1.63
    Letters
    1.56
     LETTERS
    1.53
    letters
    1.47
     LETTER
    1.42
     letter
    1.39
    letter
    1.34
     Letter
    1.30
    Letter
    1.29
    Activations Density 0.161%

    No Known Activations