© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 12955
    Prev
    Next
    INDEX
    Explanations

    terms related to structural analysis and modeling in engineering contexts

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

    Infinitive form of verbs

    np_acts-logits-general · gemini-2.0-flash

    research findings reported

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     médicaments
    -0.57
     découvertes
    -0.57
    styleUrls
    -0.57
     vérit
    -0.55
     scoper
    -0.53
     boîtier
    -0.53
    <?
    -0.52
     préoccup
    -0.52
     extranjero
    -0.52
     médicament
    -0.52
    POSITIVE LOGITS
     viceversa
    0.95
    }^{+\
    0.86
     evidences
    0.85
    cfr
    0.76
    Nowadays
    0.76
     preliminar
    0.73
     planification
    0.73
     confortable
    0.72
     tradu
    0.71
     lenght
    0.71
    Activations Density 2.786%

    No Known Activations