© 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. 6791
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to the practical application and translation of research into actionable outcomes

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

    phrases related to translating or converting knowledge into practical application.

    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
    webElement
    -0.55
    новниш
    -0.45
     CreateTagHelper
    -0.40
    AddTagHelper
    -0.38
    Hochspringen
    -0.38
    lastIndexOf
    -0.37
     razonable
    -0.36
     oyna
    -0.36
     zwier
    -0.36
    unknownFields
    -0.36
    POSITIVE LOGITS
    practical
    0.77
     realisation
    0.75
     practical
    0.74
     вопло
    0.73
     implementation
    0.72
     realization
    0.72
    Practical
    0.72
     practicality
    0.71
     reality
    0.69
     realities
    0.67
    Activations Density 0.208%

    No Known Activations