© 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. 15-GEMMASCOPE-RES-16K
    6. 3097
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical trial design and drug efficacy evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.60
    Tembelea
    -0.59
    DockStyle
    -0.57
    HostException
    -0.55
    ngdoc
    -0.53
     MonoBehaviour
    -0.51
     Khart
    -0.50
    ElementException
    -0.49
     resourceCulture
    -0.49
     виправивши
    -0.49
    POSITIVE LOGITS
     efficacy
    0.97
     superiority
    0.95
     effectiveness
    0.94
     Efficacy
    0.84
     Effectiveness
    0.81
     performance
    0.80
    Efficacy
    0.78
    effectiveness
    0.78
     demonstrated
    0.76
    Effectiveness
    0.75
    Activations Density 1.425%

    No Known Activations