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. 3-GEMMASCOPE-RES-16K
    6. 5925
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or specific terms related to academic or technical subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saveButton
    -0.57
    
    -0.51
    /***/
    -0.47
     disambiguazione
    -0.47
    ExecuteReader
    -0.46
    getRuntime
    -0.45
    GenerationType
    -0.45
    elux
    -0.44
    irp
    -0.44
    Erstellt
    -0.43
    POSITIVE LOGITS
    pper
    0.70
    PCell
    0.68
    Capp
    0.68
     Annu
    0.66
     mma
    0.66
    Посилання
    0.65
     Abb
    0.63
    ształ
    0.62
    pp
    0.62
    Abb
    0.62
    Activations Density 0.768%

    No Known Activations