© 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. 16-GEMMASCOPE-RES-16K
    11. 5359
    Prev
    Next
    INDEX
    Explanations

    references to authors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens preceding proper nouns or titles

    np_acts-logits-general · gemini-2.0-flash

    names and roles followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comprennent
    -0.64
     removeFrom
    -0.56
     Becoming
    -0.55
     quedará
    -0.55
     qued
    -0.54
     occupe
    -0.54
     contribué
    -0.53
    Bayes
    -0.53
     became
    -0.52
     partecipa
    -0.52
    POSITIVE LOGITS
     AssemblyTitle
    0.67
     Италијани
    0.58
     intent
    0.57
     تانيه
    0.56
     intention
    0.53
    =$?
    0.53
    новниш
    0.53
     Réponses
    0.53
    MLLoader
    0.51
    исленность
    0.51
    Activations Density 0.369%

    No Known Activations