© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2025
    Prev
    Next
    INDEX
    Explanations

    references to modern topics, changes over time, or comparisons to present-day situations

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

    discussion of historical or temporal changes across different time periods.

    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
    Personensuche
    -0.56
     BoxFit
    -0.50
     AssemblyTitle
    -0.46
     oprot
    -0.45
     Biôgrafia
    -0.43
    LabelTagHelper
    -0.41
    contentLoaded
    -0.41
    oredCriteria
    -0.41
     RISERVATA
    -0.40
    Personendaten
    -0.40
    POSITIVE LOGITS
     modern
    1.04
    modern
    0.93
     contemporary
    0.88
    现代
    0.85
    Modern
    0.84
     modernos
    0.82
     современ
    0.81
     modernen
    0.81
    現代
    0.81
     moderne
    0.80
    Activations Density 0.300%

    No Known Activations