© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15290
    Prev
    Next
    INDEX
    Explanations

    key terms related to individual liberty and its implications within various contexts

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

    preceding "while"

    np_acts-logits-general · gemini-2.0-flash

    conjunctions like while and but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.70
    GEBURTSDATUM
    -0.69
    DoubleQuotes
    -0.68
    protoimpl
    -0.68
     Италијани
    -0.65
    tagext
    -0.64
    exitRule
    -0.63
    gnore
    -0.62
     internetowa
    -0.61
     joaat
    -0.60
    POSITIVE LOGITS
     while
    2.74
    while
    2.42
     whilst
    2.19
     WHILE
    2.10
     mientras
    2.07
     While
    2.00
    While
    1.98
     enquanto
    1.98
     mentre
    1.92
    WHILE
    1.88
    Activations Density 0.450%

    No Known Activations