© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6688
    Prev
    Next
    INDEX
    Explanations

    terms related to digital platforms and tools in a business context

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

    Factors/elements impacting a process

    np_acts-logits-general · gemini-2.0-flash

    business operations and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amarillas
    -0.54
     interessa
    -0.52
     détruire
    -0.52
     stället
    -0.50
     experimentally
    -0.50
     Californie
    -0.49
     marié
    -0.49
     nommé
    -0.49
     haría
    -0.49
    を開始
    -0.49
    POSITIVE LOGITS
    saraba
    1.07
     availability
    1.03
     size
    0.92
     considerations
    0.92
     فريبيس
    0.89
     timing
    0.85
     selection
    0.82
     choices
    0.81
     requirements
    0.80
     preferences
    0.79
    Activations Density 0.923%

    No Known Activations