© 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. 20-GEMMASCOPE-RES-16K
    11. 11318
    Prev
    Next
    INDEX
    Explanations

    references to specific consumer electronics products and their features

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

    "TV" or "television" related terms

    np_acts-logits-general · gemini-2.0-flash

    TV Box, set-top box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.68
    UnsafeEnabled
    -0.65
    Illustrator
    -0.61
    RectangleBorder
    -0.61
    routeProvider
    -0.60
    enschaft
    -0.59
     MotionEvent
    -0.56
     Exactos
    -0.56
    CellStyle
    -0.55
     térmico
    -0.55
    POSITIVE LOGITS
     TV
    1.39
     television
    1.24
    TV
    1.20
     tv
    1.19
     Television
    1.17
    tv
    1.12
     TVs
    1.08
     Tv
    1.07
     televisions
    1.05
    Television
    1.03
    Activations Density 0.305%

    No Known Activations