© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 4978
    Prev
    Next
    INDEX
    Explanations

    references to outsourcing and related concepts

    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
    tal
    -0.77
    the
    -0.73
    tre
    -0.72
    tle
    -0.70
    tres
    -0.70
    tar
    -0.69
    tas
    -0.69
    pot
    -0.69
    plash
    -0.68
    tra
    -0.68
    POSITIVE LOGITS
    ing
    0.54
     ujednoznacz
    0.49
    chenkt
    0.44
    draft
    0.43
     referrerpolicy
    0.42
    קישורים
    0.40
    ted
    0.40
    SEGUIR
    0.40
    ות
    0.40
    IBarButtonItem
    0.37
    Activations Density 0.450%

    No Known Activations