© 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. 5498
    Prev
    Next
    INDEX
    Explanations

    details related to electronic devices and their specifications

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

    Numbers within technical specifications

    np_acts-logits-general · gemini-2.0-flash

    classifications and quantity indicators

    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
    Hentet
    -0.72
    tigma
    -0.67
    .")
    -0.64
    Kilder
    -0.64
    mặt
    -0.64
    neſs
    -0.64
    }))
    -0.63
    Unmarshaller
    -0.63
    IndentedString
    -0.63
     للمعارف
    -0.63
    POSITIVE LOGITS
    pin
    0.53
    gang
    0.52
     types
    0.49
     stages
    0.49
     sorts
    0.48
     stage
    0.45
     modes
    0.43
    modus
    0.42
    oz
    0.42
    way
    0.42
    Activations Density 0.219%

    No Known Activations