© 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. 24-GEMMASCOPE-RES-16K
    6. 4107
    Prev
    Next
    INDEX
    Explanations

    expressions of loyalty and allegiance among characters

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

    Follows titles or royalty terms

    np_acts-logits-general · gemini-2.0-flash

    princess, sorcerer, Duke, Conqueror, Queen, inventor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     personne
    -0.58
    thums
    -0.55
     للمعارف
    -0.55
     상세
    -0.54
    contentLoaded
    -0.52
    ThroughAttribute
    -0.52
    twimg
    -0.52
     NSCoder
    -0.51
    ViewFeatures
    -0.50
     >=",
    -0.50
    POSITIVE LOGITS
     Execution
    0.55
     execution
    0.54
     voyant
    0.53
     hunch
    0.52
     Nazare
    0.51
     industriels
    0.51
     espectro
    0.51
    execution
    0.50
    XmlType
    0.50
     shepherd
    0.50
    Activations Density 0.305%

    No Known Activations