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. 22-GEMMASCOPE-RES-16K
    6. 13932
    Prev
    Next
    INDEX
    Explanations

    JavaScript object property assignments and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Real
    -0.57
    Real
    -0.54
     {
    -0.52
    iale
    -0.49
    Alone
    -0.47
     espar
    -0.47
    itz
    -0.47
    GEBURTSDATUM
    -0.47
    杞
    -0.47
    melidir
    -0.46
    POSITIVE LOGITS
    SBATCH
    0.92
     Мексичка
    0.79
    anmoins
    0.72
    rouvez
    0.67
    dafx
    0.67
    SharedDtor
    0.67
     TextInputType
    0.67
    AnchorStyles
    0.66
    NUMX
    0.65
    sonian
    0.65
    Activations Density 0.131%

    No Known Activations