© 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. 13081
    Prev
    Next
    INDEX
    Explanations

    numerical references and citations related to texts or documents

    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
    brainly
    -0.55
    oved
    -0.48
     dietro
    -0.47
    ectoria
    -0.47
    IsContent
    -0.47
     bullies
    -0.46
     Needham
    -0.46
    Története
    -0.45
    orien
    -0.45
    новништво
    -0.45
    POSITIVE LOGITS
    Portale
    0.68
     chi̍t
    0.60
    AndEndTag
    0.56
    بوابة
    0.56
     antemano
    0.54
    toHaveBeenCalled
    0.54
     contactez
    0.54
     kiệm
    0.52
    ValueStyle
    0.52
    Personendaten
    0.51
    Activations Density 0.470%

    No Known Activations