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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12438
    Prev
    Next
    INDEX
    Explanations

    references to healthy subjects and tissues in a medical context

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

    Healthy/normal samples or subjects

    np_acts-logits-general · gemini-2.0-flash

    healthy subjects or controls

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ModelExpression
    -0.63
     nakalista
    -0.49
     autorytatywna
    -0.47
    NameInMap
    -0.34
    GIVEREF
    -0.33
     fortemente
    -0.33
    UnifiedTopology
    -0.31
     Италијани
    -0.31
     Gerichts
    -0.30
    HasForeignKey
    -0.29
    POSITIVE LOGITS
     innocent
    0.85
    Normal
    0.84
     Normal
    0.83
    normal
    0.80
    innocent
    0.76
     undamaged
    0.75
     Innocent
    0.75
     innocence
    0.75
    Innoc
    0.74
    正常
    0.74
    Activations Density 1.410%

    No Known Activations