© 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. 11571
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about various topics

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

    "what" followed by a pronoun or verb

    np_acts-logits-general · gemini-2.0-flash

    what followed by pronouns or verbs

    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
     AssemblyCompany
    -0.76
    UnusedPrivate
    -0.69
    AutoScaleMode
    -0.59
    stateProvider
    -0.59
     betweenstory
    -0.59
    AddWithValue
    -0.56
    ArrowToggle
    -0.55
    IntoConstraints
    -0.55
     مشين
    -0.53
     préféré
    -0.53
    POSITIVE LOGITS
     happens
    1.02
     we
    1.00
     they
    0.96
     happened
    0.93
     kind
    0.85
     you
    0.80
    hever
    0.78
    soever
    0.78
    ſo
    0.77
     else
    0.76
    Activations Density 0.127%

    No Known Activations