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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12365
    Prev
    Next
    INDEX
    Explanations

    references to intelligence-related themes and phenomena

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

    ending in "olog," "ision," "imb," "LED," or "RAT."

    np_acts-logits-general · gemini-2.0-flash

    plural nouns and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сылкі
    -0.65
     Normdatei
    -0.64
    copg
    -0.61
    ufficient
    -0.60
    exitRule
    -0.59
    interopRequire
    -0.57
     aDecoder
    -0.57
    mybatisplus
    -0.56
    \{\\
    -0.55
    PRNewswire
    -0.53
    POSITIVE LOGITS
    s
    3.96
    ی
    1.52
    ся
    1.50
    ы
    1.46
    ים
    1.37
    ات
    1.24
    sı
    1.14
    schen
    1.10
    sver
    1.05
    sted
    1.05
    Activations Density 1.209%

    No Known Activations