© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2437
    Prev
    Next
    INDEX
    Explanations

    instances of the toLowerCase function, indicating a focus on text transformation or normalization

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

    programming-related code patterns, specifically methods involving string manipulation and lowercasing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.65
     Geſch
    -0.62
     ſeine
    -0.60
     dieſer
    -0.59
     ſeinen
    -0.59
    HttpEntity
    -0.58
     müſſen
    -0.58
    IBarButtonItem
    -0.57
    zarchiwizowane
    -0.57
     dieſen
    -0.56
    POSITIVE LOGITS
    toLowerCase
    0.68
    toUpperCase
    0.64
    UVWXYZ
    0.55
    equalsIgnoreCase
    0.53
    downcase
    0.49
    uppercase
    0.47
    lowercase
    0.45
     strtolower
    0.44
    strtolower
    0.44
     uppercase
    0.44
    Activations Density 0.069%

    No Known Activations