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. 5-GEMMASCOPE-RES-16K
    6. 13094
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions that involve sets and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.82
    StoryboardSegue
    -0.81
     BitmapFactory
    -0.79
    DockStyle
    -0.79
    homonymie
    -0.78
    verwijspagina
    -0.74
    äsident
    -0.71
    KURZBESCHREIBUNG
    -0.71
    endphp
    -0.71
     LIABLE
    -0.69
    POSITIVE LOGITS
     Bigg
    0.57
    {\"
    0.57
     مُعرِّف
    0.57
     fine
    0.53
    っ
    0.53
     cold
    0.52
    onRequest
    0.52
     larges
    0.51
     largest
    0.51
    {\
    0.50
    Activations Density 0.120%

    No Known Activations