© 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. 35-GEMMASCOPE-RES-16K
    11. 7144
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to experimental studies on tumors and cancer in mice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patients
    -0.52
     Patient
    -0.49
     patient
    -0.49
    Patient
    -0.48
     patients
    -0.47
     nakalista
    -0.46
    Patients
    -0.46
    patient
    -0.46
    PATIENT
    -0.45
     GetEnumerator
    -0.45
    POSITIVE LOGITS
     mice
    0.94
     rats
    0.92
     animals
    0.88
     Animals
    0.82
     Mice
    0.80
     Rats
    0.75
    Animals
    0.75
    Mice
    0.75
    Rats
    0.74
    animals
    0.72
    Activations Density 2.524%

    No Known Activations