© 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. 25-GEMMASCOPE-RES-16K
    11. 7301
    Prev
    Next
    INDEX
    Explanations

    expressions that emphasize clarity and transparency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.79
    DrawerToggle
    -0.70
    OGND
    -0.61
    Cordialement
    -0.61
    WebMethod
    -0.59
    الإنجليزية
    -0.59
    yntaxException
    -0.58
    Hozzáférés
    -0.56
     TÉCN
    -0.55
    RequiresApi
    -0.54
    POSITIVE LOGITS
    cut
    1.16
     cut
    1.03
    Cut
    0.88
     Cut
    0.85
     skies
    0.77
    CUT
    0.76
    cuts
    0.75
    inghouse
    0.73
     CUT
    0.73
    cutting
    0.72
    Activations Density 0.180%

    No Known Activations