© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 12802
    Prev
    Next
    INDEX
    Explanations

    elements related to characters, particularly focusing on digits and string manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 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
     ویکی‌پدی
    -0.52
    __(/*!
    -0.51
    letoe
    -0.46
     CURIAM
    -0.45
     surla
    -0.44
     arşivlendi
    -0.44
    rrggbb
    -0.43
     intptr
    -0.42
     Wiktionnaire
    -0.42
     uterine
    -0.41
    POSITIVE LOGITS
    isdigit
    0.68
     digits
    0.68
    digits
    0.64
    strconv
    0.58
     numerals
    0.58
     díg
    0.56
    Digits
    0.56
     chiffres
    0.54
     numbers
    0.54
     chiffre
    0.52
    Activations Density 0.494%

    No Known Activations