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

    Neuronpedia

    Jacobian LensNEW
    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. 16-GEMMASCOPE-RES-16K
    11. 3221
    Prev
    Next
    INDEX
    Explanations

    assertions and qualifiers related to validity and acceptability

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

    Preceding forms of "to be" (is, was, are, etc.)

    np_acts-logits-general · gemini-2.0-flash

    is not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     however
    -0.63
     же
    -0.57
     ovviamente
    -0.57
    Obviously
    -0.56
    によると
    -0.56
     obviously
    -0.55
     entanto
    -0.54
    сюда
    -0.54
    oso
    -0.53
     oczywiście
    -0.53
    POSITIVE LOGITS
    IntoConstraints
    1.18
     فريبيس
    1.08
     المعيارى
    1.00
     Normdatei
    0.97
    bootstrapcdn
    0.94
    extAlignment
    0.94
     صوتيه
    0.94
    ScopeManager
    0.93
     ویکی‌پدیا
    0.91
     وتسجيلات
    0.91
    Activations Density 0.743%

    No Known Activations