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. 80104
    Prev
    Next
    INDEX
    Explanations

    significant concepts related to inquiry and exploration

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

    goals, idea, plate, punches, truth, money, day, question

    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
    spesies
    -0.52
    تقاوى
    -0.48
    Personendaten
    -0.46
     évaluation
    -0.46
     unterkunft
    -0.45
     sanitarios
    -0.44
    GEBURTSDATUM
    -0.43
     orgánico
    -0.40
     nourriture
    -0.40
    ERÍA
    -0.40
    POSITIVE LOGITS
     ब्रेकडाउन
    0.54
     slick
    0.50
    存于互联网档案馆
    0.49
     useRouter
    0.47
    ✨:
    0.46
    httphttps
    0.46
     PEP
    0.46
    Sv
    0.45
     pips
    0.44
     busted
    0.44
    Activations Density 0.063%

    No Known Activations