© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11066
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements in scientific contexts

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

    numeric values in scientific/mathematical contexts, particularly ratios and measurements.

    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
    ływ
    -0.26
    preuves
    -0.24
     veden
    -0.24
     Orten
    -0.23
    <unused63>
    -0.22
     novas
    -0.21
    <unused60>
    -0.21
    PRES
    -0.21
    <unused61>
    -0.21
    ENODEV
    -0.21
    POSITIVE LOGITS
    sidemargin
    0.79
    RTLR
    0.77
    extAlignment
    0.73
    irited
    0.68
    OGND
    0.68
    parsedMessage
    0.68
     tartalomajánló
    0.66
    ValueStyle
    0.66
    RegistryLite
    0.65
    ScopeManager
    0.65
    Activations Density 0.438%

    No Known Activations