© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 933
    Prev
    Next
    INDEX
    Explanations

    formatted data structures and their parameters or values

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

    Plus signs, plus/minus strands, or positive

    np_acts-logits-general · gemini-2.0-flash

    + or -

    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
    HttpDelete
    -0.79
     Minus
    -0.68
     downgrade
    -0.67
    Minus
    -0.67
    offline
    -0.66
     Offline
    -0.66
     disapproval
    -0.65
    descend
    -0.64
    dislike
    -0.64
    decreasing
    -0.63
    POSITIVE LOGITS
     positive
    1.02
     positives
    0.91
     Positive
    0.88
    glEnable
    0.87
    Positive
    0.85
    =+
    0.84
     positively
    0.84
    ,+
    0.82
    positive
    0.80
    }_{+
    0.74
    Activations Density 0.969%

    No Known Activations