© 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. 1968
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical information

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

    numerical data, especially numbers and percentages.

    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
    Portail
    -0.54
    parsedMessage
    -0.47
     Италијани
    -0.46
     tartalomajánló
    -0.45
     bezeichneter
    -0.43
    ArgumentParser
    -0.42
    رشف
    -0.39
    FormTagHelper
    -0.39
    LoggerFactory
    -0.38
     prioriti
    -0.38
    POSITIVE LOGITS
     closer
    0.50
     worse
    0.45
     nearer
    0.45
    __["
    0.44
    󠁣
    0.43
    NUMX
    0.41
     tougher
    0.40
     expensive
    0.40
     addirittura
    0.40
     muualla
    0.39
    Activations Density 0.380%

    No Known Activations