© 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. 20-GEMMASCOPE-RES-16K
    11. 15934
    Prev
    Next
    INDEX
    Explanations

    expressions that denote mathematical functions and their properties

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

    Mathematical expressions with interval notation

    np_acts-logits-general · gemini-2.0-flash

    in interval notation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ējās
    -0.56
    Surface
    -0.44
     surface
    -0.44
     dip
    -0.43
    Tre
    -0.42
    SURFACE
    -0.41
     Tre
    -0.41
    surface
    -0.40
    hér
    -0.40
    Collections
    -0.39
    POSITIVE LOGITS
     interval
    1.20
     $[
    1.20
     $[-
    1.15
     Interval
    1.15
     [-
    1.14
     INTERVAL
    1.07
    }=[
    1.06
    =[
    1.06
    Interval
    1.02
    interval
    0.99
    Activations Density 0.786%

    No Known Activations