© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27636
    Prev
    Next
    INDEX
    Explanations

    terms related to behavioral therapy and its statistical evaluation involving twins

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

    experiments and mechanisms

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    WebServlet
    -0.71
     auffi
    -0.71
    GHIJKLM
    -0.70
     crdi
    -0.67
    manship
    -0.66
    ^(@)
    -0.66
    capulco
    -0.65
    etheless
    -0.64
     ainfi
    -0.64
     المعيارى
    -0.63
    POSITIVE LOGITS
    例文帳に追加
    0.79
    IInterface
    0.65
     defaultstate
    0.58
    </blockquote>
    0.57
    ativement
    0.57
     ...
    0.56
    LookAnd
    0.55
     дописавши
    0.54
    Identyfik
    0.52
    0.51
    Activations Density 0.027%

    No Known Activations