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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8325
    Prev
    Next
    INDEX
    Explanations

    Java class definitions and their components

    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
    <bos>
    -0.89
    )];
    
    -0.63
    ParallelGroup
    -0.58
    Personensuche
    -0.58
     VIDEOTAPE
    -0.58
    ?
    
    -0.57
    transQ
    -0.55
    __))
    -0.50
    tvguidetime
    -0.48
    例句
    -0.48
    POSITIVE LOGITS
    subpackage
    0.65
    itatis
    0.64
    ärna
    0.63
    XmlRootElement
    0.58
     AssemblyTitle
    0.58
    EClass
    0.57
    hasRole
    0.57
     Maha
    0.57
     laude
    0.57
     aprile
    0.56
    Activations Density 0.193%

    No Known Activations