© 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. 22-GEMMASCOPE-RES-16K
    6. 6300
    Prev
    Next
    INDEX
    Explanations

    company names and their associated financial terms or results

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

    Biopharmaceutical company updates and regulatory approvals

    np_acts-logits-general · gemini-2.0-flash

    biologics and drug approvals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    로그램
    -0.45
     nech
    -0.44
    putstr
    -0.44
    Sport
    -0.43
     bles
    -0.42
    nEnter
    -0.41
     Deportes
    -0.40
     HttpStatus
    -0.40
    ámb
    -0.40
     Diesel
    -0.39
    POSITIVE LOGITS
     biolog
    0.94
     Orphan
    0.86
    Orphan
    0.83
    oredCriteria
    0.83
     drug
    0.82
     bio
    0.82
     biologic
    0.81
     FDA
    0.80
     <<<<<<<<<<<<<<
    0.78
     Bio
    0.77
    Activations Density 1.150%

    No Known Activations