Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16392
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms related to health conditions and treatments

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

    A colon appearing either in wiki interlanguage links (typically preceded by a two-letter language code) or at the end of academic/medical article titles written in brackets.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SharedDtor
    -0.54
    IndentedString
    -0.53
     betweenstory
    -0.52
     '\\;'
    -0.50
    DockStyle
    -0.50
    脚注の使い方
    -0.50
     Limitations
    -0.46
     verona
    -0.46
    ípio
    -0.45
    ifflin
    -0.45
    POSITIVE LOGITS
    abestanden
    0.54
    principalTable
    0.43
    prüche
    0.41
    GEBURTSDATUM
    0.39
     незавершена
    0.38
    uesia
    0.36
     gynhyrchwyd
    0.35
    ']>;
    0.34
    DeleteBehavior
    0.34
    cloudfront
    0.32
    Activations Density 0.092%

    No Known Activations