© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3849
    Prev
    Next
    INDEX
    Explanations

    actions related to taking things away or removing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fill
    -0.52
    Fill
    -0.51
    Werdegang
    -0.44
    átní
    -0.44
     drep
    -0.44
     gând
    -0.44
     echar
    -0.44
     kaarangay
    -0.42
    ząd
    -0.42
    ANCY
    -0.41
    POSITIVE LOGITS
     removed
    1.17
     remove
    1.11
     Removing
    1.11
     removes
    1.10
     Removed
    1.08
     removing
    1.06
     REMOVE
    1.04
     Removes
    1.04
     Remove
    1.04
     Removal
    1.04
    Activations Density 0.388%

    No Known Activations