© 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. 18-GEMMASCOPE-RES-16K
    11. 15431
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of a legal or formal question

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

    Follows a variety of question words

    np_acts-logits-general · gemini-2.0-flash

    which, court, all, OB, should, metal, <

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.35
     Roskov
    -1.32
     kasarigan
    -1.20
     tartalomajánló
    -1.18
     سكانية
    -1.18
     kaarangay
    -1.17
    __':
    -1.15
    +#+#
    -1.14
    WebElementEntity
    -1.14
     Audiodateien
    -1.13
    POSITIVE LOGITS
    </em>
    0.57
    </h2>
    0.51
    '
    0.50
    F
    0.49
    -
    0.47
    P
    0.47
    And
    0.47
    ''
    0.47
    1
    0.47
    E
    0.46
    Activations Density 0.463%

    No Known Activations