© 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. 15295
    Prev
    Next
    INDEX
    Explanations

    markers indicating the beginning of text segments

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

    that start a sentence or clause

    np_acts-logits-general · gemini-2.0-flash

    Introduction, About, When

    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
     entanto
    -1.07
    прочем
    -0.75
     however
    -0.75
     furthermore
    -0.74
    但也
    -0.74
    Revenir
    -0.73
     obstante
    -0.72
    uttavia
    -0.71
    however
    -0.71
     but
    -0.70
    POSITIVE LOGITS
    When
    1.11
     When
    1.08
     Cuando
    0.85
    During
    0.83
     During
    0.83
     Since
    0.82
    Since
    0.81
    After
    0.80
    Sometimes
    0.80
     After
    0.79
    Activations Density 0.602%

    No Known Activations