© 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. 38-GEMMASCOPE-RES-16K
    11. 10397
    Prev
    Next
    INDEX
    Explanations

    phrases indicating guidelines, principles, or formulations related to materials or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    consulté
    -0.48
    chle
    -0.40
    もしれない
    -0.37
    klus
    -0.36
    opoulos
    -0.36
    ister
    -0.36
     Ledger
    -0.35
    іод
    -0.35
    óz
    -0.35
     halla
    -0.35
    POSITIVE LOGITS
     thereof
    2.55
     thereon
    2.09
     therefrom
    2.03
     thereto
    2.00
     therewith
    1.92
     therein
    1.88
     thereunder
    1.61
     therefor
    1.60
     thereupon
    1.60
     davon
    1.46
    Activations Density 0.895%

    No Known Activations