© 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. 9350
    Prev
    Next
    INDEX
    Explanations

    references to languages and their translations

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

    Languages (other than English)

    np_acts-logits-general · gemini-2.0-flash

    identifying languages

    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
    Hochspringen
    -0.87
    tagHelperRunner
    -0.86
    ConstraintMaker
    -0.82
    Atsauces
    -0.75
    "]];
    -0.70
    ()]);
    -0.69
     cherchés
    -0.69
    enderror
    -0.69
    RenderAtEndOf
    -0.67
    "]);
    -0.67
    POSITIVE LOGITS
     speaking
    0.66
    speaking
    0.60
     version
    0.57
    BlockingQueue
    0.54
     Version
    0.51
     versions
    0.51
    denomin
    0.50
     language
    0.50
    圏
    0.49
    sprach
    0.49
    Activations Density 0.209%

    No Known Activations