© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    references to assumptions, judgments, or comparisons related to people's attitudes or appearances

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

    Sentences starting with "This is," "It is," or "An."

    np_acts-logits-general · gemini-2.0-flash

    This is another

    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
     pertanto
    -0.73
     مرئيه
    -0.68
     např
    -0.57
     Therefore
    -0.56
     perciò
    -0.56
    何况
    -0.55
     TextInputType
    -0.55
     derfor
    -0.55
    SourceChecksum
    -0.55
     obstante
    -0.54
    POSITIVE LOGITS
    こちらも
    1.11
    これも
    1.02
     another
    1.01
    another
    0.89
     ebenfalls
    0.85
    Another
    0.85
     probably
    0.85
    Somewhat
    0.81
    Probably
    0.81
     surprisingly
    0.80
    Activations Density 0.272%

    No Known Activations