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. 15-GEMMASCOPE-RES-16K
    6. 8541
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or operations involving variables and constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeneratedMessage
    -0.55
     مخطط
    -0.51
     berta
    -0.50
    ']))
    
    -0.49
    pří
    -0.48
    /***/
    -0.48
    toMatchSnapshot
    -0.47
    EDEFAULT
    -0.47
     świ
    -0.46
    تول
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.62
     jsPsych
    0.62
     Sucre
    0.62
     MenuView
    0.62
    ########.
    0.60
     inversa
    0.60
     umgekehrt
    0.59
     obverse
    0.58
    clusal
    0.58
     inverse
    0.57
    Activations Density 0.731%

    No Known Activations