© 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. 4151
    Prev
    Next
    INDEX
    Explanations

    references to energy-related statements or criticisms

    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
    󠁥
    -0.72
    󠁷
    -0.40
     Banten
    -0.40
     fara
    -0.36
    Kansas
    -0.36
     Keene
    -0.35
    神奈川
    -0.34
     Kakashi
    -0.34
     jTextField
    -0.34
     Goddard
    -0.34
    POSITIVE LOGITS
     Scottish
    1.95
    Scottish
    1.78
     Scotland
    1.77
     Scots
    1.64
    Scotland
    1.63
     scottish
    1.63
     Glasgow
    1.55
     Edinburgh
    1.49
     Scotsman
    1.45
     Scot
    1.44
    Activations Density 0.414%

    No Known Activations