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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 85869
    Prev
    Next
    INDEX
    Explanations

    the concept of "essential" in various contexts

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

    essential

    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
     Inscrivez
    -0.62
     للمعارف
    -0.60
     igång
    -0.59
     ainfi
    -0.59
     Suivez
    -0.57
    astéroïdes
    -0.57
     LoginForm
    -0.56
     informée
    -0.55
     Noviembre
    -0.55
     tatuagem
    -0.55
    POSITIVE LOGITS
     Essential
    1.13
    Essential
    1.10
    essential
    1.07
     essential
    1.04
     Essentials
    0.86
    essentials
    0.82
     essentials
    0.81
     esenciales
    0.81
     indispens
    0.75
     essenziale
    0.75
    Activations Density 0.008%

    No Known Activations