© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14218
    Prev
    Next
    INDEX
    Explanations

    discussions about the possibility and implementation of concepts or actions

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

    Comes after "can" or "possible"

    np_acts-logits-general · gemini-2.0-flash

    possibility or ability

    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
     onCreateView
    -0.99
    ThroughAttribute
    -0.85
     Taktlose
    -0.78
     >=",
    -0.75
     Waray
    -0.75
    новниш
    -0.70
    +#+#
    -0.68
     calendriers
    -0.66
    protoimpl
    -0.66
    TagMode
    -0.65
    POSITIVE LOGITS
     durchaus
    0.55
     easily
    0.55
    omalainen
    0.55
     pretty
    0.54
     almost
    0.53
     form
    0.49
    sequelize
    0.46
     very
    0.46
    ism
    0.45
     even
    0.44
    Activations Density 0.457%

    No Known Activations