© 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. 1-GEMMASCOPE-RES-16K
    11. 3597
    Prev
    Next
    INDEX
    Explanations

    mentions of varied categories or types within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    показа
    -0.49
    的是
    -0.49
    ↵↵
    -0.47
     environmental
    -0.44
    isRequired
    -0.43
    Location
    -0.42
    ↵
    -0.42
    document
    -0.42
    <eos>
    -0.42
    endar
    -0.41
    POSITIVE LOGITS
     range
    2.28
     ranges
    1.41
     RANGE
    1.35
     assortment
    1.35
     variety
    1.31
    range
    1.24
     gamme
    1.20
    variety
    1.16
     array
    1.15
     gamut
    1.12
    Activations Density 0.149%

    No Known Activations