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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 93054
    Prev
    Next
    INDEX
    Explanations

    terms related to standalone functionality and independence

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

    standalone, alone, own, itself

    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
     Erwachsene
    -0.26
    ↵
    -0.26
     yakın
    -0.25
     yoktur
    -0.24
     óptica
    -0.24
     místo
    -0.23
     dieselben
    -0.23
     scène
    -0.23
     soon
    -0.23
     posiciones
    -0.23
    POSITIVE LOGITS
     standalone
    0.88
    standalone
    0.82
     Itself
    0.80
    Standalone
    0.76
    itself
    0.76
     itſelf
    0.74
    BorderFactory
    0.71
     самостоя
    0.71
    alone
    0.70
     itself
    0.70
    Activations Density 0.042%

    No Known Activations