© 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. 15393
    Prev
    Next
    INDEX
    Explanations

    temporal phrases and prepositions indicating time-related contexts

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

    "during" followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    during the

    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
     Cæsar
    -0.95
    évaluateur
    -0.90
    Personendaten
    -0.87
     ModelExpression
    -0.87
     Silurian
    -0.84
     Shakspeare
    -0.83
     initComponents
    -0.81
     himſelf
    -0.80
     Sopho
    -0.80
    AnimationsModule
    -0.77
    POSITIVE LOGITS
     the
    1.46
     a
    1.17
     an
    1.02
     their
    0.93
     some
    0.88
     its
    0.87
     those
    0.84
     our
    0.84
     these
    0.82
     both
    0.80
    Activations Density 0.749%

    No Known Activations