© 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. 7450
    Prev
    Next
    INDEX
    Explanations

    terms related to consent and approval in research contexts

    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
    клопе
    -0.40
    záll
    -0.37
    unnitel
    -0.36
    chowa
    -0.36
    AsUp
    -0.35
    KURZBESCHREIBUNG
    -0.33
    iastes
    -0.33
    újo
    -0.33
    deleteAll
    -0.32
    deleteById
    -0.32
    POSITIVE LOGITS
     obtain
    2.56
     obtaining
    2.53
     obtained
    2.48
     obtains
    2.36
     Obtaining
    2.28
     Obtain
    2.27
    obtain
    2.16
     Obtained
    2.13
    obtained
    2.13
    Obtain
    2.11
    Activations Density 1.947%

    No Known Activations