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. 1-GEMMASCOPE-RES-16K
    6. 7053
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to marine biology and microbial genetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    قایناقلار
    -0.48
    __':
    
    -0.47
     okuyayım
    -0.45
    FUNC
    -0.45
    rophoresis
    -0.45
    ข้าว
    -0.44
    rawd
    -0.44
    ುತ್ತ
    -0.44
     proceed
    -0.43
     Straight
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.81
    
    0.80
    principalColumn
    0.71
     Majefty
    0.67
    Zitat
    0.66
     ThemeData
    0.65
    ⓧ
    0.65
    ica
    0.63
    setCellStyle
    0.62
     Administrativna
    0.62
    Activations Density 2.127%

    No Known Activations