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. 5-GEMMASCOPE-RES-16K
    6. 5027
    Prev
    Next
    INDEX
    Explanations

    phrases with the preposition "of" and other related conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.79
     "");
    
    -0.77
    []>(
    -0.76
     ""}
    -0.76
    formik
    -0.73
    }{*}{
    -0.73
    ()]
    
    -0.73
    )、
    -0.71
    >");
    
    -0.70
     Ballard
    -0.69
    POSITIVE LOGITS
     Anfitrión
    0.78
    quele
    0.76
     Of
    0.73
     And
    0.71
     fibres
    0.69
     brancas
    0.69
     يتيمه
    0.67
     verksam
    0.66
     considérons
    0.64
     vermelhas
    0.64
    Activations Density 0.115%

    No Known Activations