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. 24-GEMMASCOPE-RES-16K
    6. 8515
    Prev
    Next
    INDEX
    Explanations

    references to collections and generic types in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related tokens after periods

    np_acts-logits-general · gemini-2.0-flash

    reserved in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.62
    chaun
    -0.60
    __':
    -0.58
    håll
    -0.56
    __':
    
    -0.55
    namentales
    -0.55
    Swag
    -0.53
     sanitaires
    -0.53
    umentación
    -0.53
    daos
    -0.52
    POSITIVE LOGITS
    Generic
    1.05
     Generic
    0.74
    Specialized
    0.68
     generic
    0.67
    ObjectModel
    0.65
    Concurrent
    0.64
    generic
    0.64
     gener
    0.59
     nahilalakip
    0.58
     ExecuteAsync
    0.54
    Activations Density 0.064%

    No Known Activations