© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3790
    Prev
    Next
    INDEX
    Explanations

    software development concepts and terminologies related to programming languages and frameworks

    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
     MenuView
    -0.59
    tagHelperRunner
    -0.54
     StringTokenizer
    -0.52
    struts
    -0.51
     виправивши
    -0.50
    ilever
    -0.48
    WebElementEntity
    -0.48
    alty
    -0.48
     препратки
    -0.48
    Descripció
    -0.47
    POSITIVE LOGITS
     rust
    0.79
     Rust
    0.79
    Rust
    0.72
    rust
    0.63
     Cargo
    0.55
     cargo
    0.53
    cargo
    0.50
    Cargo
    0.49
     rusty
    0.46
     cargoes
    0.45
    Activations Density 0.957%

    No Known Activations