© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10793
    Prev
    Next
    INDEX
    Explanations

    terms related to cytotoxicity and the effects of plant extracts on cancer cells

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pushFollow
    -0.71
     MessageBoxIcon
    -0.69
     wireType
    -0.66
    DrawerToggle
    -0.63
    COLN
    -0.62
    GEBURTSDATUM
    -0.62
    DataPropertyName
    -0.60
    PhysRevD
    -0.58
     nég
    -0.57
     "..\..\
    -0.56
    POSITIVE LOGITS
     assays
    0.69
     assay
    0.67
     inhibition
    0.66
     cytotoxicity
    0.65
     assayed
    0.59
    Спољашње
    0.57
     Inhibition
    0.56
     Assays
    0.55
     titration
    0.52
     pharmacology
    0.52
    Activations Density 2.192%

    No Known Activations