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. 20-GEMMASCOPE-RES-16K
    6. 14275
    Prev
    Next
    INDEX
    Explanations

    specific terms related to medical or biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.77
    RTRS
    -0.71
    noinspection
    -0.66
    Enfin
    -0.64
    InstrumentedTest
    -0.62
    hdashline
    -0.60
    Hentet
    -0.60
    PyExc
    -0.60
    ScopeManager
    -0.59
     onPause
    -0.59
    POSITIVE LOGITS
     towards
    0.67
     kepada
    0.60
     of
    0.60
     into
    0.58
     about
    0.57
     to
    0.54
     terhadap
    0.53
     on
    0.52
     with
    0.52
     toward
    0.51
    Activations Density 0.932%

    No Known Activations