© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 121718
    Prev
    Next
    INDEX
    Explanations

    the act of investigating or examining various topics or phenomena

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

    objective to investigate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.59
     tartalomajánló
    -0.59
    ReusableCell
    -0.57
    GEBURTSDATUM
    -0.54
    complexContent
    -0.51
    Tikang
    -0.50
     Seeder
    -0.48
    bitol
    -0.47
    Comté
    -0.47
     CURIAM
    -0.45
    POSITIVE LOGITS
     investigate
    1.09
     investigates
    0.93
     investigating
    0.93
     Investigate
    0.89
     investigated
    0.85
     Investigating
    0.76
     investigar
    0.72
     explore
    0.70
    Explore
    0.65
     exploring
    0.65
    Activations Density 0.013%

    No Known Activations