© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12879
    Prev
    Next
    INDEX
    Explanations

    expressions of spirituality and requests for divine assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.56
    OGND
    -0.56
    Bored
    -0.54
    zerne
    -0.52
    RegistryLite
    -0.52
    WithIOException
    -0.51
     Bored
    -0.51
    Diweddarwch
    -0.50
    heb
    -0.50
     &___
    -0.49
    POSITIVE LOGITS
    bewah
    0.59
    CROSSTALK
    0.56
     möge
    0.52
    InteropServices
    0.52
     vœ
    0.51
    TestingModule
    0.51
    kháu
    0.50
     cappello
    0.50
     desiderio
    0.49
     pioggia
    0.48
    Activations Density 0.083%

    No Known Activations