© 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. 37-GEMMASCOPE-RES-16K
    11. 5871
    Prev
    Next
    INDEX
    Explanations

    terms related to proper configurations and appropriate actions or standards in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     úspě
    -0.46
     يتيمه
    -0.41
     successfully
    -0.40
     dôle
    -0.38
     successful
    -0.38
    successfully
    -0.37
     siker
    -0.37
    success
    -0.37
    successful
    -0.34
    webElementGuid
    -0.34
    POSITIVE LOGITS
     sized
    0.77
     transfieras
    0.67
     مشين
    0.65
    sized
    0.63
    Geplaatst
    0.62
     amount
    0.61
     proportions
    0.61
     SafeMath
    0.60
     proportioned
    0.59
    erweise
    0.58
    Activations Density 0.740%

    No Known Activations