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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 91737
    Prev
    Next
    INDEX
    Explanations

    future tense verbs and the phrases associated with intent or action

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

    "I'll" or "I will" followed by verbs

    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
     autorytatywna
    -0.76
    complexContent
    -0.57
    IntoConstraints
    -0.54
     CreateTagHelper
    -0.47
    SurfaceView
    -0.45
    thâu
    -0.45
     itself
    -0.44
     ujednoznacz
    -0.44
     obyvateľov
    -0.44
     disambiguazione
    -0.44
    POSITIVE LOGITS
     أنا
    0.50
     choose
    0.47
    SuppressLint
    0.46
    我可以
    0.45
    etera
    0.44
     apologise
    0.44
     apologize
    0.43
    setMinimum
    0.43
     revise
    0.42
     CHOOSE
    0.42
    Activations Density 0.023%

    No Known Activations