© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 5787
    Prev
    Next
    INDEX
    Explanations

    experiences or reports of medical conditions and injuries

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

    negative outcomes after experience

    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
     betweenstory
    -0.40
    artamentos
    -0.37
     mor
    -0.34
    irited
    -0.33
    rinology
    -0.32
     politics
    -0.32
    듦
    -0.32
     comparte
    -0.30
     IDisposable
    -0.30
     inoxydable
    -0.30
    POSITIVE LOGITS
     experiencing
    0.65
     mengalami
    0.61
    OCCURRED
    0.58
     experienced
    0.57
    Datuak
    0.56
     Experienced
    0.50
    experienced
    0.50
    Experienced
    0.50
     dialami
    0.49
    Exper
    0.49
    Activations Density 0.193%

    No Known Activations