© 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. 990
    Prev
    Next
    INDEX
    Explanations

    terms related to containers and their functionality

    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
    Erreferentziak
    -0.48
     doInBackground
    -0.42
    NameInMap
    -0.40
    GEBURTSDATUM
    -0.39
     énon
    -0.39
    engertian
    -0.38
     Италијани
    -0.38
    gehenden
    -0.38
    Résumé
    -0.37
    Diweddarwch
    -0.37
    POSITIVE LOGITS
     bottle
    2.36
     bottles
    2.23
     Bottle
    2.00
    bottle
    2.00
     Bottles
    1.95
    Bottle
    1.89
     BOTT
    1.87
    bottles
    1.80
    Bott
    1.70
     botella
    1.66
    Activations Density 0.335%

    No Known Activations