© 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. 25-GEMMASCOPE-RES-16K
    6. 4070
    Prev
    Next
    INDEX
    Explanations

    references to health and medical services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     econômica
    -0.72
    ighborhood
    -0.70
     demais
    -0.68
     vectorielle
    -0.67
    AVOR
    -0.65
    personalized
    -0.65
     eorum
    -0.64
     econô
    -0.63
    Analyzed
    -0.63
     harbors
    -0.63
    POSITIVE LOGITS
     (£
    0.77
     enquiry
    0.71
     programme
    0.71
     Organiser
    0.65
     enquiries
    0.64
     licence
    0.64
    
    0.63
     organiser
    0.62
     supremo
    0.61
    hoea
    0.61
    Activations Density 0.463%

    No Known Activations