© 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. 3471
    Prev
    Next
    INDEX
    Explanations

    references to medical professionals and institutions

    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
    riwal
    -0.39
    Tributes
    -0.38
    Ifc
    -0.37
     الرياضيه
    -0.36
     gyhoeddwyd
    -0.35
    MergeFrom
    -0.35
    ilares
    -0.35
    szönöm
    -0.34
    THESIS
    -0.34
    tains
    -0.33
    POSITIVE LOGITS
     tell
    2.78
     told
    2.42
     telling
    2.38
     Tell
    2.38
     tells
    2.36
    Tell
    2.30
    tell
    2.17
     TELL
    2.09
    tells
    1.95
     Telling
    1.93
    Activations Density 0.555%

    No Known Activations