© 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. 9005
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structural elements in text

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

    Code, punctuation, or HTML snippets

    np_acts-logits-general · gemini-2.0-flash

    end of code statements

    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
     Tenth
    -0.53
    eqn
    -0.52
     ten
    -0.51
    hexane
    -0.50
     six
    -0.50
    Còn
    -0.49
     Mortimer
    -0.48
    ঞ
    -0.47
     ruote
    -0.47
    ontal
    -0.47
    POSITIVE LOGITS
    StructEnd
    0.88
    <h3>
    0.78
     resourceCulture
    0.73
    లాలు
    0.71
    IonicModule
    0.67
    )++;
    0.65
     Paglinawan
    0.64
    الإنجليزية
    0.63
    ArgumentParser
    0.62
    RenderAtEndOf
    0.61
    Activations Density 0.119%

    No Known Activations