© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1141
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نص
    -0.47
    iad
    -0.46
    ragment
    -0.44
     prote
    -0.44
     more
    -0.43
    ABSTRACT
    -0.43
     مشين
    -0.42
    мар
    -0.42
     دیگری
    -0.42
    olf
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    0.93
     nahilalakip
    0.88
     оригіналу
    0.80
    mtrl
    0.80
     FetchType
    0.79
    +:+
    0.73
     GenerationType
    0.69
    WebServlet
    0.67
    XmlAccessType
    0.65
    原始内容存档于
    0.65
    Activations Density 0.276%

    No Known Activations