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. 3412
    Prev
    Next
    INDEX
    Explanations

    phrases discussing exceptions to rules or norms

    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
    racene
    -0.66
     MaterialApp
    -0.61
    DispatchToProps
    -0.55
    eburger
    -0.52
    gara
    -0.51
    <eos>
    -0.50
    zyła
    -0.50
    DIR
    -0.50
     kol
    -0.49
     Des
    -0.49
    POSITIVE LOGITS
     exceptions
    1.56
     exception
    1.50
     Exceptions
    1.45
    exceptions
    1.29
    例外
    1.29
     Ausnahme
    1.28
     excep
    1.22
     excepted
    1.16
    exception
    1.13
    Exceptions
    1.13
    Activations Density 0.255%

    No Known Activations