© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8949
    Prev
    Next
    INDEX
    Explanations

    references to API definitions and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.63
    IndentedString
    -0.53
    BorderFactory
    -0.53
     Class
    -0.52
     $?
    -0.50
    .?
    -0.49
    enterOuterAlt
    -0.48
     Paglinawan
    -0.48
    zości
    -0.48
     lining
    -0.47
    POSITIVE LOGITS
    pub
    1.05
    fn
    0.94
     fn
    0.87
    #[
    0.85
     pub
    0.83
    impl
    0.80
    abestanden
    0.72
     Pub
    0.67
    mod
    0.64
    Pub
    0.62
    Activations Density 0.220%

    No Known Activations