© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11237
    Prev
    Next
    INDEX
    Explanations

    significant contextual markers in the text, indicating the start of a new section or a change in topic

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

    HTML or number followed by a period

    np_acts-logits-general · gemini-2.0-flash

    2 fractures

    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
     PyLong
    -0.48
     Open
    -0.47
    rawQuery
    -0.46
     tand
    -0.45
    FailureListener
    -0.45
     disc
    -0.45
    zo
    -0.44
    lack
    -0.43
    obot
    -0.43
     республики
    -0.43
    POSITIVE LOGITS
     متعلقه
    1.05
    expandindo
    0.93
     GenerationType
    0.78
     disambiguazione
    0.77
     tartalomajánló
    0.70
    tvguidetime
    0.69
     cherchés
    0.69
     TimeUnit
    0.69
     arşivlendi
    0.65
    rungsseite
    0.63
    Activations Density 0.030%

    No Known Activations