© 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. 18-GEMMASCOPE-RES-16K
    11. 6562
    Prev
    Next
    INDEX
    Explanations

    terms associated with cancer treatments and drug efficacy in research

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

    Cancer cell lines

    np_acts-logits-general · gemini-2.0-flash

    cancer cell lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.78
    AndEndTag
    -0.68
     htons
    -0.66
    ChildScrollView
    -0.62
     BoxDecoration
    -0.60
    IntoConstraints
    -0.59
     IDA
    -0.58
    MethodManager
    -0.56
     pageable
    -0.55
     Jazeera
    -0.55
    POSITIVE LOGITS
     cells
    0.65
     cell
    0.62
    expandindo
    0.54
    cell
    0.54
     Cell
    0.53
     Zellen
    0.53
     CELL
    0.53
    sizeCache
    0.52
     CELLS
    0.50
    Cell
    0.50
    Activations Density 1.134%

    No Known Activations