© 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. 43281
    Prev
    Next
    INDEX
    Explanations

    references to time and schedules

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

    time of day and periods

    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
    contentLoaded
    -0.57
     informée
    -0.53
     esternos
    -0.52
     nonUne
    -0.52
     Administrativna
    -0.45
    Personendaten
    -0.44
     GenerationType
    -0.44
    quedas
    -0.43
    AndroidJUnit
    -0.43
    GEBURTS
    -0.43
    POSITIVE LOGITS
     evening
    0.51
     morning
    0.44
    XmlAccessType
    0.44
     daytime
    0.43
     starting
    0.43
     evenings
    0.43
     until
    0.42
     nightly
    0.41
    evening
    0.41
     safety
    0.41
    Activations Density 0.019%

    No Known Activations