Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 61797
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to succession in a royal or political context

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

    successor or succession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    9
    -0.46
    punten
    -0.42
     &
    -0.41
     box
    -0.41
    Normalized
    -0.41
     dandy
    -0.41
    hrter
    -0.40
    τζ
    -0.40
     crazy
    -0.40
     Bark
    -0.40
    POSITIVE LOGITS
     successor
    1.05
     successors
    0.88
     succession
    0.87
    successor
    0.85
     Succession
    0.82
     Nachfolger
    0.79
     useHistory
    0.72
     predecessor
    0.72
     succes
    0.71
     HasFactory
    0.67
    Activations Density 0.015%

    No Known Activations