Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 112082
    Prev
    Next
    INDEX
    Explanations

    references to the city of Orlando and the Miranda rights

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

    Miranda warning rights

    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
    s
    -0.44
    Check
    -0.39
     check
    -0.39
    subsubsection
    -0.38
     Check
    -0.37
    b
    -0.35
     tež
    -0.34
    ➩
    -0.33
     Fä
    -0.33
    check
    -0.33
    POSITIVE LOGITS
     Orlando
    1.32
    Orlando
    1.25
     orlando
    0.96
     myſelf
    0.83
    celotti
    0.78
    roland
    0.70
     Roland
    0.69
    ChildScrollView
    0.68
     BrowserModule
    0.67
    lando
    0.66
    Activations Density 0.007%

    No Known Activations