© 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. 10-GEMMASCOPE-RES-16K
    11. 8400
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional or alternative situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.66
     normaux
    -0.63
     vectorielles
    -0.63
    ArgsConstructor
    -0.61
     Agamemnon
    -0.59
    WebControls
    -0.59
     мәкал
    -0.57
     CreateTagHelper
    -0.56
     kasarigan
    -0.55
     chiare
    -0.55
    POSITIVE LOGITS
     الحره
    0.59
    erom
    0.58
    ÁG
    0.57
    gama
    0.54
    %";
    0.53
    licht
    0.53
     human
    0.52
    boten
    0.51
    &=&\
    0.51
    sequently
    0.51
    Activations Density 0.498%

    No Known Activations