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. 14404
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or code structure

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

    HTML or code tags

    np_acts-logits-general · gemini-2.0-flash

    code and special characters

    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
     miniaturka
    -0.55
     Wikiseite
    -0.53
     rheinland
    -0.50
     württemberg
    -0.50
     nélk
    -0.49
     kapture
    -0.45
     parachoque
    -0.45
     hırka
    -0.45
    genodigd
    -0.44
     nordrhein
    -0.44
    POSITIVE LOGITS
    Filmographie
    0.49
    });*/
    0.48
    Données
    0.48
    ...");
    
    0.46
    })*/
    0.43
    Ligações
    0.42
    Ä
    0.42
    Risultati
    0.41
    knapp
    0.41
     Kole
    0.41
    Activations Density 0.738%

    No Known Activations