© 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 EvalsExportsinterp-engineNEWAPI 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. 1208
    Prev
    Next
    INDEX
    Explanations

    expressions indicating confusion or lack of clarity in communication

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

    Followed by JSON/code or a number

    np_acts-logits-general · gemini-2.0-flash

    Jets mentioning "4"

    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
    HtmlAttribute
    -1.01
     '\\;'
    -0.91
     AssemblyCulture
    -0.90
    Geplaatst
    -0.88
    numerusform
    -0.86
    FormTagHelper
    -0.85
     Paglinawan
    -0.84
    GEBURTSDATUM
    -0.84
    Vorlage
    -0.79
    IsMutable
    -0.78
    POSITIVE LOGITS
     Hügel
    0.39
    ecta
    0.37
    <h2>
    0.36
    ofType
    0.36
     owne
    0.35
    Hi
    0.35
    ñora
    0.35
    ''');
    0.34
    ">:
    0.34
    Multiline
    0.34
    Activations Density 0.013%

    No Known Activations