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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 82
    Prev
    Next
    INDEX
    Explanations

    terms related to quality assessments and measurements

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

    technical or professional quality measurements across different domains like medical testing, image quality, audit performance, and agricultural research.

    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
    脚注の使い方
    -0.71
    WithIOException
    -0.68
    findpost
    -0.66
     <<<<<<<<<<<<<<
    -0.65
    帖最后由
    -0.64
     виправивши
    -0.64
    quelize
    -0.64
    المناصب
    -0.64
    ArgsConstructor
    -0.63
     ſind
    -0.63
    POSITIVE LOGITS
     deterioration
    0.49
     morale
    0.49
     integridad
    0.48
     integrity
    0.47
     stability
    0.45
     qualidade
    0.44
     estabilidad
    0.44
     progrès
    0.43
     movilidad
    0.43
    ctility
    0.43
    Activations Density 0.544%

    No Known Activations