© 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. 2-GEMMASCOPE-RES-16K
    11. 7370
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and technical terms related to scientific analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.81
     للاسماء
    -0.78
     BoxFit
    -0.77
     Exactos
    -0.77
     snippetHide
    -0.75
     חיצוניים
    -0.75
    AndEndTag
    -0.73
     <=",
    -0.73
    Personendaten
    -0.72
     arşivlendi
    -0.72
    POSITIVE LOGITS
    di
    1.02
    ity
    0.69
     tanto
    0.56
    DI
    0.52
    ITY
    0.51
     Pal
    0.50
     trans
    0.49
    TabIndex
    0.49
    dikan
    0.44
    CN
    0.44
    Activations Density 2.043%

    No Known Activations