Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2363
    Prev
    Next
    INDEX
    Explanations

    references to locations, entities, or notable events

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

    "Superlative adjectives followed by a noun."

    np_acts-logits-general · gemini-2.0-flash

    the superlative

    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
     hosszú
    -0.71
     kanssa
    -0.64
     högre
    -0.64
     particulières
    -0.64
    bootstrapcdn
    -0.62
     preocupes
    -0.60
     egna
    -0.58
     motivadoras
    -0.58
     élevées
    -0.58
     espagne
    -0.58
    POSITIVE LOGITS
     StatefulWidget
    0.78
     leggi
    0.73
     whit
    0.69
    =$?
    0.69
     StatelessWidget
    0.67
     ris
    0.66
     surla
    0.66
     smo
    0.66
    NUMX
    0.64
     loos
    0.62
    Activations Density 0.177%

    No Known Activations