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. 23-GEMMASCOPE-RES-16K
    6. 5611
    Prev
    Next
    INDEX
    Explanations

    references to technological advancements and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.59
    __":
    
    -0.57
    وام
    -0.56
    onViewCreated
    -0.55
    OrNil
    -0.55
     geométrico
    -0.50
     riemp
    -0.50
     BeautifulSoup
    -0.49
     actualité
    -0.48
    ăn
    -0.48
    POSITIVE LOGITS
     switch
    2.91
     switching
    2.76
     transition
    2.67
     switched
    2.59
     Switching
    2.50
    Switching
    2.47
     switches
    2.46
     transitioning
    2.44
     Switch
    2.38
     transitioned
    2.36
    Activations Density 0.829%

    No Known Activations