© 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. 9021
    Prev
    Next
    INDEX
    Explanations

    positive or negative sentiments expressed through various emotional descriptors

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

    Followed by digits, often related to transitions or coordinates

    np_acts-logits-general · gemini-2.0-flash

    numerical sequences and code

    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
     FetchType
    -0.76
    ISupport
    -0.68
     onAnimation
    -0.67
    apimachinery
    -0.66
    Personensuche
    -0.64
     pinulongan
    -0.64
    <bos>
    -0.62
    Rujuakan
    -0.62
     оригіналу
    -0.61
     gambe
    -0.61
    POSITIVE LOGITS
     الدولى
    0.55
    tagez
    0.54
    InputBorder
    0.53
    ghijkl
    0.47
    ghijklmnop
    0.47
    ghed
    0.46
    %;">
    0.44
     Theſe
    0.44
     فريبيس
    0.43
     "..\..\
    0.42
    Activations Density 0.445%

    No Known Activations