© 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. 3330
    Prev
    Next
    INDEX
    Explanations

    terms related to immigration, nationality, and origin

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

    "origin" or "source."

    np_acts-logits-general · gemini-2.0-flash

    place of origin or source

    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
     الحره
    -0.73
    RenderAtEndOf
    -0.60
    EndProject
    -0.59
     useParams
    -0.59
    
    -0.57
    WriteBarrier
    -0.57
    VersionUID
    -0.56
    msgTypes
    -0.56
    #
    -0.56
    Опис
    -0.55
    POSITIVE LOGITS
     origin
    1.86
     source
    1.83
    source
    1.58
     origen
    1.54
    origin
    1.51
     origins
    1.49
     Source
    1.43
     Origin
    1.41
    Origin
    1.39
     origem
    1.38
    Activations Density 0.441%

    No Known Activations