© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15502
    Prev
    Next
    INDEX
    Explanations

    references to human health and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteMapping
    -0.48
     Trouvez
    -0.47
     saia
    -0.43
     offerte
    -0.43
     znamen
    -0.43
    __
    -0.42
     graduation
    -0.42
    ItemCount
    -0.41
     sociologists
    -0.41
     insegu
    -0.40
    POSITIVE LOGITS
     patients
    1.58
    patients
    1.10
     subjects
    1.03
     Patients
    1.02
     patient
    0.99
     individuals
    0.98
     patienter
    0.95
     pacientes
    0.95
     adults
    0.93
    Patients
    0.93
    Activations Density 1.623%

    No Known Activations