© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 955
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "to be" and related gerunds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Karsten
    -0.63
    addContainerGap
    -0.60
    laughing
    -0.59
    DoubleQuotes
    -0.58
    ettare
    -0.57
    TextBoxColumn
    -0.57
     fråga
    -0.56
    hdys
    -0.56
     ganger
    -0.55
    ComponentScan
    -0.55
    POSITIVE LOGITS
    FieldBuilder
    0.78
     PLWABN
    0.70
     NUKAT
    0.70
    DeleteBehavior
    0.70
     being
    0.69
    ness
    0.69
     BEING
    0.69
     Being
    0.68
     hObject
    0.68
     bein
    0.67
    Activations Density 0.109%

    No Known Activations