© 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. 20-GEMMASCOPE-RES-16K
    6. 10522
    Prev
    Next
    INDEX
    Explanations

    terms related to analysis and classification in various contexts

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

    Preceding words/text before "based"

    np_acts-logits-general · gemini-2.0-flash

    on the basis of

    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
    ]--;
    -0.69
    \{\\
    -0.58
     ویکی‌پدیا
    -0.57
    DispatchToProps
    -0.54
    RectangleBorder
    -0.54
     Roskov
    -0.54
     FileNotFound
    -0.51
    bewerken
    -0.48
    illeurs
    -0.48
    ]++;
    -0.48
    POSITIVE LOGITS
     based
    3.03
     Based
    2.61
     BASED
    2.52
    Based
    2.48
    based
    2.37
     basing
    2.13
     baseado
    2.07
     basé
    2.06
    BASED
    2.06
     basado
    2.04
    Activations Density 1.007%

    No Known Activations