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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11494
    Prev
    Next
    INDEX
    Explanations

    words related to a specific and recurring theme associated with 'Th'

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

    "Th" followed by a letter

    np_acts-logits-general · gemini-2.0-flash

    words starting with th

    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
    \}^{
    -0.63
    er
    -0.59
    uter
    -0.56
    andır
    -0.56
    +#+#
    -0.54
    <h3>
    -0.54
    <h2>
    -0.53
    #![
    -0.52
    riscoll
    -0.51
     Andree
    -0.51
    POSITIVE LOGITS
     TH
    0.72
    oughly
    0.69
    IntoConstraints
    0.68
    MigrationBuilder
    0.66
    omeness
    0.65
    WireFormatLite
    0.65
    Personendaten
    0.65
    QMetaType
    0.65
    Bibliograf
    0.64
    ruptedException
    0.64
    Activations Density 0.404%

    No Known Activations