© 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. 14851
    Prev
    Next
    INDEX
    Explanations

    actions and modifications related to adjusting, editing, or manipulating objects or parameters

    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
    quial
    -0.54
     CanadaChoose
    -0.51
    Демографія
    -0.49
    providedIn
    -0.49
    directly
    -0.48
     vindicated
    -0.48
    PageContext
    -0.47
    ValueStyle
    -0.47
     Fizz
    -0.47
    revalidate
    -0.47
    POSITIVE LOGITS
     accordingly
    0.93
     appropriately
    0.89
     according
    0.67
    according
    0.63
     adecuadamente
    0.60
     slik
    0.59
     suitably
    0.59
     affinch
    0.58
    ให้
    0.58
     into
    0.58
    Activations Density 1.058%

    No Known Activations