© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122074
    Prev
    Next
    INDEX
    Explanations

    questions and phrases indicating inquiry or curiosity

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

    both or all

    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
    tauan
    -0.42
     osallist
    -0.41
     mukana
    -0.38
     túnel
    -0.37
     Nationen
    -0.37
     vastaan
    -0.36
     serca
    -0.35
     mitään
    -0.35
     suerte
    -0.35
     löytyy
    -0.35
    POSITIVE LOGITS
    contentLoaded
    0.69
    Ambos
    0.63
     Ambos
    0.61
    どちらも
    0.60
     ambos
    0.60
     Both
    0.57
     Beide
    0.55
     both
    0.54
     begge
    0.54
    httphttps
    0.53
    Activations Density 0.001%

    No Known Activations