© 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. 7552
    Prev
    Next
    INDEX
    Explanations

    the term "Sa" and its variations, which likely indicate a relevance to South African contexts or entities

    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
    bital
    -0.47
     addSubview
    -0.45
    NewGuid
    -0.43
    ActionCreators
    -0.42
    PMailer
    -0.42
    withOpacity
    -0.41
    astify
    -0.40
     Photocase
    -0.40
    lesias
    -0.40
     propOrder
    -0.40
    POSITIVE LOGITS
     disambiguazione
    0.49
    хьтан
    0.41
     Scalars
    0.39
     gawas
    0.36
     gonzález
    0.35
    Portály
    0.35
     pamamagitan
    0.35
    profits
    0.35
    tonsoft
    0.35
    nordic
    0.34
    Activations Density 0.235%

    No Known Activations