© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1324
    Prev
    Next
    INDEX
    Explanations

    statistical data and survey results related to populations

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

    Types and methods of sampling

    np_acts-logits-general · gemini-2.0-flash

    sampling methods and representativeness

    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
    SharedCtor
    -0.90
    الحياه
    -0.75
    StoryboardSegue
    -0.72
    AddTagHelper
    -0.68
     propOrder
    -0.67
     Theſe
    -0.65
    Enllaços
    -0.65
    tableFuture
    -0.62
     déchir
    -0.62
     Efq
    -0.61
    POSITIVE LOGITS
     sample
    2.03
    sample
    1.80
     sampling
    1.73
     samples
    1.71
     Sample
    1.68
    Sample
    1.68
     SAMPLE
    1.60
     Sampling
    1.55
     sampled
    1.47
     Samples
    1.47
    Activations Density 0.594%

    No Known Activations