© 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. 2644
    Prev
    Next
    INDEX
    Explanations

    texts related to medical research and peer-reviewed publications

    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
    Portail
    -0.54
    CppMethod
    -0.49
    ForRow
    -0.47
    umman
    -0.46
     IndexPath
    -0.45
    спонд
    -0.45
     okuyayım
    -0.45
    ToScroll
    -0.44
     Acuerdo
    -0.43
    IVEREF
    -0.43
    POSITIVE LOGITS
     يا
    0.61
    ،
    0.57
    NameInMap
    0.56
    ⓧ
    0.55
     uintptr
    0.54
     كه
    0.53
     به
    0.53
     Thacker
    0.52
     در
    0.52
     rembour
    0.51
    Activations Density 0.042%

    No Known Activations