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. 14-GEMMASCOPE-RES-16K
    6. 7586
    Prev
    Next
    INDEX
    Explanations

    instances of message handling and update structures in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleable
    -0.50
    RSpec
    -0.49
    CloseOperation
    -0.47
     pre
    -0.47
    Self
    -0.46
     angolo
    -0.42
     Self
    -0.42
    Personensuche
    -0.42
    okhttp
    -0.42
    findpost
    -0.41
    POSITIVE LOGITS
     detailed
    0.71
    detailed
    0.67
     Detailed
    0.66
    ARROLLO
    0.66
     Bure
    0.63
    Detailed
    0.62
     detail
    0.60
    詳細
    0.58
     <<<<<<<<<<<<<<
    0.57
     OFDb
    0.57
    Activations Density 0.558%

    No Known Activations