© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 812
    Prev
    Next
    INDEX
    Explanations

    references to permissions and actions related to adding and removing items from lists or collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, deletion, or removal-related words

    np_acts-logits-general · gemini-2.0-flash

    remove or delete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.76
    ativistic
    -0.58
     AssemblyTitle
    -0.57
    RLock
    -0.54
     Feeder
    -0.52
    jsonwebtoken
    -0.51
     للمعارف
    -0.51
     SqlDbType
    -0.49
    styleType
    -0.49
    Feeding
    -0.49
    POSITIVE LOGITS
     removal
    2.57
     remove
    2.36
     removing
    2.32
     removed
    2.31
     Removal
    2.30
     Remove
    2.13
     Removing
    2.09
    removal
    2.09
     REMOV
    2.04
    Removal
    2.03
    Activations Density 1.151%

    No Known Activations