© 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. 25-GEMMASCOPE-RES-16K
    11. 7745
    Prev
    Next
    INDEX
    Explanations

    references to significant or notable individuals and their achievements or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FontOfSize
    -0.64
    不同的
    -0.64
     основном
    -0.63
     olika
    -0.62
     مختلف
    -0.61
     different
    -0.61
     forskellige
    -0.61
    createNewFile
    -0.59
     مختلفة
    -0.58
    Different
    -0.58
    POSITIVE LOGITS
     ever
    1.61
     imaginable
    1.44
     EVER
    1.38
    ever
    1.12
     jamás
    1.12
     anywhere
    1.11
     possible
    1.04
    之一
    1.03
     ooit
    1.03
     conceivable
    1.03
    Activations Density 0.331%

    No Known Activations