© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9222
    Prev
    Next
    INDEX
    Explanations

    the word "certain" in various contexts

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

    Followed by quantities, types, or categories

    np_acts-logits-general · gemini-2.0-flash

    certain type or group

    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
     hydropower
    -0.50
     hydro
    -0.49
     hyd
    -0.47
     Flüs
    -0.44
    </i>
    -0.44
     Penga
    -0.43
    Hydro
    -0.42
     Loss
    -0.42
     Spy
    -0.42
     morts
    -0.41
    POSITIVE LOGITS
    Certain
    1.02
     Certain
    1.01
    certain
    1.00
     certain
    0.96
     CERTAIN
    0.93
     certaine
    0.80
     ciertos
    0.76
     tertentu
    0.74
     ciertas
    0.74
     bepaalde
    0.73
    Activations Density 0.095%

    No Known Activations