Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6336
    Prev
    Next
    INDEX
    Explanations

    technical terms related to application functionalities and web operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.69
    зулта
    -0.68
    MigrationBuilder
    -0.65
    исленность
    -0.61
     AssemblyCompany
    -0.58
    oa̍t
    -0.56
    BufferException
    -0.56
    IsContent
    -0.56
    __))
    -0.55
     Toler
    -0.54
    POSITIVE LOGITS
    ciutto
    0.53
    trino
    0.52
    MotionEvent
    0.51
     muualla
    0.49
     MotionEvent
    0.49
    Ingestion
    0.49
    tto
    0.49
    quiries
    0.48
     насељу
    0.47
    férés
    0.47
    Activations Density 0.719%

    No Known Activations