© 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. 3345
    Prev
    Next
    INDEX
    Explanations

    references to records or the concept of recording in various contexts

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

    SQL database query syntax and database-related text.

    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
     Wis
    -0.59
     Bou
    -0.53
    Wis
    -0.52
    5
    -0.50
    fuse
    -0.50
    authService
    -0.50
    Themen
    -0.50
    Bou
    -0.49
    The
    -0.48
    Hey
    -0.48
    POSITIVE LOGITS
     record
    1.31
    record
    1.23
     Record
    1.17
     records
    1.12
     RECORD
    1.11
    Record
    1.09
    RECORD
    1.07
    records
    1.05
     Records
    1.00
     RECORDS
    1.00
    Activations Density 0.070%

    No Known Activations