© 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. 8-GEMMASCOPE-RES-16K
    11. 7463
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to reasons and justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.71
    lgari
    -0.67
    CppMethod
    -0.59
     censiti
    -0.54
     صوتيه
    -0.50
    OGND
    -0.47
     FishBase
    -0.46
    unteer
    -0.46
    र्ष
    -0.46
     Audiodateien
    -0.45
    POSITIVE LOGITS
     mourut
    0.76
     descendre
    0.74
     quelcon
    0.72
     mourir
    0.70
     étoit
    0.69
     actuelles
    0.66
     rendus
    0.63
    KEYCODE
    0.63
     juger
    0.63
     indietro
    0.63
    Activations Density 1.524%

    No Known Activations