© 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
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7400
    Prev
    Next
    INDEX
    Explanations

    statements related to medical conditions and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     passaggio
    -0.64
    scattering
    -0.63
    reve
    -0.63
     useStyles
    -0.60
    labeling
    -0.59
     réalis
    -0.59
     bacio
    -0.58
     annealing
    -0.57
    كتشاف
    -0.57
    pressing
    -0.56
    POSITIVE LOGITS
     looked
    0.79
     studied
    0.73
     checked
    0.71
     considered
    0.70
     given
    0.69
     dealt
    0.67
     examined
    0.66
     evaluated
    0.66
     taken
    0.65
     worked
    0.65
    Activations Density 1.376%

    No Known Activations