© 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. 1280
    Prev
    Next
    INDEX
    Explanations

    mentions of experimental results related to "resist in" within biological contexts, specifically regarding cancer and its implications

    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
    ReusableCell
    -0.76
    nesses
    -0.53
    хь
    -0.52
    Tembelea
    -0.49
    arie
    -0.48
    ikas
    -0.47
    erobe
    -0.46
    ophi
    -0.46
     censiti
    -0.45
    atitis
    -0.45
    POSITIVE LOGITS
    ThroughAttribute
    0.81
    AddTagHelper
    0.76
    tocin
    0.74
    AndEndTag
    0.72
     noDo
    0.72
     itſelf
    0.72
     alone
    0.68
    RefNanny
    0.67
    تقاوى
    0.67
    IVEREF
    0.66
    Activations Density 1.265%

    No Known Activations