© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9476
    Prev
    Next
    INDEX
    Explanations

    academic topics related to science and mathematics

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

    industry or field-specific content, particularly when mentioned with related technical terms or concepts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    WaitGroup
    -0.53
     disponibilités
    -0.53
    LookAnd
    -0.53
    MultipartFile
    -0.52
    IntoConstraints
    -0.52
    reactstrap
    -0.50
    usercontent
    -0.49
    ardless
    -0.49
    IsPostBack
    -0.49
    期刊论文
    -0.47
    POSITIVE LOGITS
     للاسماء
    0.43
     Cognition
    0.42
    楽部
    0.39
     område
    0.39
     izquier
    0.39
     darb
    0.38
     noix
    0.37
     écrans
    0.37
    ziehungen
    0.36
     related
    0.36
    Activations Density 0.651%

    No Known Activations