© 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. 3923
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to database interactions and data structure definitions

    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
    Cyfeiriadau
    -0.51
     betweenstory
    -0.50
     NUKAT
    -0.48
     hikariConfig
    -0.47
    CodeAttribute
    -0.47
    afficheront
    -0.47
    EndGlobalSection
    -0.46
    harusnya
    -0.46
    windowFixed
    -0.45
    лтамалар
    -0.44
    POSITIVE LOGITS
     matches
    0.53
     match
    0.49
     similarities
    0.48
     includes
    0.47
    match
    0.46
     GLO
    0.44
     resembles
    0.44
     include
    0.44
     resemb
    0.43
    includes
    0.43
    Activations Density 0.231%

    No Known Activations