© 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. 15-GEMMASCOPE-RES-16K
    11. 2576
    Prev
    Next
    INDEX
    Explanations

    references to academic research and collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calore
    -0.52
     Versicher
    -0.51
     гале
    -0.50
    TypedDataSet
    -0.50
    fromLTRB
    -0.49
     INSURANCE
    -0.47
    chi
    -0.47
    AspNet
    -0.47
    әһ
    -0.46
    ice
    -0.46
    POSITIVE LOGITS
     research
    1.43
     researches
    1.38
    research
    1.26
     researchers
    1.25
     studies
    1.20
     researching
    1.15
     scientists
    1.14
     study
    1.12
    研究
    1.09
     onderzoek
    1.07
    Activations Density 0.823%

    No Known Activations