© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7361
    Prev
    Next
    INDEX
    Explanations

    terms related to spatial and functional elements in scientific contexts

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

    preceding conjunctions or parentheses

    np_acts-logits-general · gemini-2.0-flash

    measuring states and quantities

    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
    })));
    -0.80
    ")){
    -0.72
    Personensuche
    -0.70
    ")));
    -0.70
    '])){
    -0.68
    "):
    -0.66
    '):
    -0.66
    "),
    -0.65
    "],
    -0.65
    )"),
    -0.65
    POSITIVE LOGITS
     että
    0.81
    -,
    0.67
     maupun
    0.63
     puis
    0.61
     וגם
    0.56
     mété
    0.53
     ($)
    0.52
    だけでなく
    0.52
     lẫn
    0.52
     ProtoMessage
    0.51
    Activations Density 0.830%

    No Known Activations