© 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. 21-GEMMASCOPE-RES-16K
    11. 4516
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of removing or erasing elements or properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextAlign
    -0.65
    prepareStatement
    -0.61
    󠁿
    -0.60
     defStyleAttr
    -0.60
    Cordialement
    -0.59
     iprot
    -0.58
     textStatus
    -0.58
    LookAnd
    -0.57
    ʁ
    -0.57
     Mainly
    -0.56
    POSITIVE LOGITS
    REMOVE
    0.77
     REMOVE
    0.77
    Removes
    0.74
     Removes
    0.73
     removes
    0.69
     Removed
    0.69
    remo
    0.68
     Remove
    0.67
     entfernen
    0.67
     removed
    0.66
    Activations Density 0.122%

    No Known Activations