© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 30099
    Prev
    Next
    INDEX
    Explanations

    instances of the word "useful" and its variations

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

    useful and specifying words

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     tanggung
    -0.55
     istrinya
    -0.52
     suaminya
    -0.51
     kyse
    -0.51
    feinander
    -0.50
     kanssa
    -0.48
     bendera
    -0.46
    anzug
    -0.46
     Schmitt
    -0.45
     Chamb
    -0.45
    POSITIVE LOGITS
    useful
    1.22
     Useful
    1.12
    Useful
    1.10
     useful
    1.03
     usefulness
    0.90
     utile
    0.81
    valuable
    0.81
    useless
    0.81
    helpful
    0.80
     helpful
    0.79
    Activations Density 0.019%

    No Known Activations