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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2511
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest assistance or support

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

    "help" and its variations

    np_acts-logits-general · gemini-2.0-flash

    offering help

    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
    odacty
    -0.43
     bandeira
    -0.41
     sequência
    -0.41
     ää
    -0.36
    ****************
    -0.36
     coroa
    -0.36
     sæ
    -0.34
     Muhammadu
    -0.34
     superfície
    -0.34
     MacGregor
    -0.34
    POSITIVE LOGITS
    help
    1.23
    Help
    1.13
    helps
    1.11
     Help
    1.10
     help
    1.09
    helped
    1.07
    helping
    1.05
     Helps
    1.04
     HELP
    1.02
    Helps
    1.02
    Activations Density 0.069%

    No Known Activations