© 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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6499
    Prev
    Next
    INDEX
    Explanations

    contrasts and qualifiers in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    それとも
    -0.54
    circ
    -0.54
    ẾT
    -0.54
    riva
    -0.52
    ög
    -0.52
     ausz
    -0.51
     EDIT
    -0.51
    ネマ
    -0.51
    zhang
    -0.51
     circon
    -0.51
    POSITIVE LOGITS
     especially
    1.21
     particularly
    1.18
    especially
    1.10
    particularly
    1.09
     Particularly
    1.08
    Especially
    1.08
     especialmente
    1.04
     Especially
    1.00
    特に
    0.94
     particularmente
    0.93
    Activations Density 0.351%

    No Known Activations