© 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. 6665
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and functioning of systems or components

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

    technical or legal documentation involving precise measurements and detailed descriptions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    prepositions and their surrounding context, particularly "of" when it appears in complex technical or legal phrases.

    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
     a
    -0.32
     and
    -0.31
    Иван
    -0.31
     only
    -0.31
    ix
    -0.30
    몰
    -0.30
     ways
    -0.29
     clever
    -0.29
    calloc
    -0.29
    子上
    -0.29
    POSITIVE LOGITS
    Personendaten
    0.82
     HasFactory
    0.75
     surla
    0.73
    AccessorTable
    0.70
    MessageOf
    0.70
    CloseOperation
    0.69
     autorytatywna
    0.67
    ConstraintMaker
    0.67
    ScopeManager
    0.67
     transfieras
    0.64
    Activations Density 0.638%

    No Known Activations