Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14046
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical terms and clinical trial details related to specific medications

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

    FDA approval and medical indications

    np_acts-logits-general · gemini-2.0-flash

    drug approvals and indications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.62
    脚注の使い方
    -0.61
     drug
    -0.60
     Drug
    -0.58
    drug
    -0.58
    Drug
    -0.58
     DRUG
    -0.58
    醐
    -0.58
    drugs
    -0.57
     فريبيس
    -0.57
    POSITIVE LOGITS
     indications
    0.68
     indication
    0.68
     approved
    0.61
    getMenuInflater
    0.60
     indicated
    0.57
    iomanip
    0.57
     authorized
    0.57
     INDIC
    0.55
    Approved
    0.55
     authorised
    0.53
    Activations Density 0.981%

    No Known Activations