© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1373
    Prev
    Next
    INDEX
    Explanations

    the presence and frequency of the word "above" and its variations in context

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

    "above" appearing in text

    np_acts-logits-general · gemini-2.0-flash

    above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    neutron
    -0.40
     Akismet
    -0.40
    ч
    -0.40
    actin
    -0.39
    囗
    -0.38
    cokinetic
    -0.38
     mecan
    -0.38
    gwt
    -0.36
    NHL
    -0.35
    Wirk
    -0.35
    POSITIVE LOGITS
     above
    1.36
    Above
    1.30
     Above
    1.30
    above
    1.27
     ABOVE
    1.20
    ABOVE
    1.09
    bove
    1.00
     below
    1.00
     sopra
    0.92
     acima
    0.91
    Activations Density 0.133%

    No Known Activations