© 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. 31-GEMMASCOPE-RES-16K
    6. 12278
    Prev
    Next
    INDEX
    Explanations

    measurements and units related to physical quantities

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

    units of measurement with their abbreviations, such as mm, kg, MHz, and GPa.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    units of measurement, particularly metric units like millimeters, square meters, and other scientific quantifications.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.45
    YourGuide
    -0.42
     بيها
    -0.42
    Bronnen
    -0.41
    әрмәләр
    -0.40
    
    -0.40
     zvuky
    -0.39
    Mick
    -0.39
    cplusplus
    -0.38
    Bakgrunnsstoff
    -0.37
    POSITIVE LOGITS
    Equivalent
    0.54
     équi
    0.52
    씩
    0.49
     equivalent
    0.49
    左右
    0.48
     Equivalent
    0.47
    хьтан
    0.46
     abstrait
    0.45
    equivalent
    0.45
    /$
    0.45
    Activations Density 0.823%

    No Known Activations