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

    Neuronpedia

    Jacobian LensNEW
    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. 15773
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting in text

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    mathematical alignment and research participation

    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
    Portale
    -0.69
    SourceChecksum
    -0.63
    <eos>
    -0.54
     bas
    -0.51
    المراجع
    -0.46
     Finney
    -0.45
    Einzelnachweise
    -0.44
    Jong
    -0.43
    tsburgh
    -0.43
    بود
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    0.88
    AccessorTable
    0.65
    \}\\
    0.58
    DoubleQuotes
    0.58
     referenties
    0.57
    ArgsConstructor
    0.56
    XtraBars
    0.55
     الحره
    0.54
    Toy
    0.54
     UIAlert
    0.54
    Activations Density 0.035%

    No Known Activations