© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 8480
    Prev
    Next
    INDEX
    Explanations

    the word "partly" and similar adverbs indicating partiality or a degree of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.60
    o
    -0.58
    ylus
    -0.57
    <?
    -0.57
    sa
    -0.51
     liitty
    -0.51
    FieldDescriptor
    -0.49
     quên
    -0.48
    نج
    -0.47
     따
    -0.47
    POSITIVE LOGITS
     predominantly
    1.13
     Mostly
    1.13
    primarily
    1.09
    Mostly
    1.07
    mostly
    1.06
     Partly
    1.05
    partly
    1.03
    Partly
    1.02
    Mainly
    1.01
     mostly
    0.98
    Activations Density 0.065%

    No Known Activations