© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 1449
    Prev
    Next
    INDEX
    Explanations

    specific television networks or programming details related to broadcasts

    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
     eben
    -0.25
     Davies
    -0.24
    */].
    -0.23
     :/
    -0.22
    😒
    -0.22
     ilości
    -0.21
    😂😂😂😂
    -0.20
    😂😂
    -0.20
     
    -0.20
     س
    -0.19
    POSITIVE LOGITS
     autorytatywna
    0.94
     Efq
    0.87
    ロウィン
    0.84
    enablog
    0.84
    majánló
    0.83
    <unused43>
    0.83
    <unused41>
    0.82
    <unused14>
    0.82
    <unused3>
    0.82
    <pad>
    0.82
    Activations Density 0.197%

    No Known Activations