© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12139
    Prev
    Next
    INDEX
    Explanations

    phrases implying clarity or distinctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    onson
    -0.49
    ditionally
    -0.49
    ucket
    -0.48
    ụng
    -0.48
     endTime
    -0.47
     Mousse
    -0.46
     Robots
    -0.46
     rodents
    -0.46
    tslib
    -0.45
     Վերցված
    -0.45
    POSITIVE LOGITS
     Clear
    1.13
    Clear
    1.11
     clear
    1.09
     CLEAR
    1.05
    clear
    1.05
     clears
    0.93
    CLEAR
    0.92
     clearer
    0.84
     clearness
    0.83
     Klar
    0.83
    Activations Density 0.107%

    No Known Activations