© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10005
    Prev
    Next
    INDEX
    Explanations

    content related to the organization, acknowledgments, and corrections in academic papers

    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
    ⓧ
    -0.59
    ={({
    -0.56
     GENERATED
    -0.55
    …?
    -0.49
    phazard
    -0.48
    rzez
    -0.48
     trás
    -0.48
    nextDouble
    -0.47
    importation
    -0.47
     …”
    -0.47
    POSITIVE LOGITS
     minor
    0.70
    minor
    0.64
     typos
    0.64
     Accepted
    0.63
    Minor
    0.63
     accepted
    0.62
     Minor
    0.61
    SequentialGroup
    0.58
    unknownFields
    0.57
     matches
    0.56
    Activations Density 0.230%

    No Known Activations