© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 3929
    Prev
    Next
    INDEX
    Explanations

    terminologies and references related to nuclear energy and environmental agreements

    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
    ensement
    -0.44
     ГУ
    -0.39
     chi̍t
    -0.39
    sidemargin
    -0.39
     sosp
    -0.38
    preso
    -0.38
    WritableDatabase
    -0.38
     alté
    -0.38
     écl
    -0.37
     trän
    -0.37
    POSITIVE LOGITS
     carbon
    1.17
     decarbon
    1.11
    carbon
    1.05
    Carbon
    1.02
     Carbon
    0.99
     CARBON
    0.94
     emissions
    0.94
     climate
    0.90
    Climate
    0.90
     Emissions
    0.89
    Activations Density 0.227%

    No Known Activations