© 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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 221
    Prev
    Next
    INDEX
    Explanations

    keywords related to providing services and solutions in a business context

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

    client services and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delwed
    -0.45
    ValueStyle
    -0.43
    CloseOperation
    -0.42
     yym
    -0.42
    LLocation
    -0.40
    setVerticalGroup
    -0.39
    Билгалдахарш
    -0.38
     onPostExecute
    -0.38
     gynhyrchwyd
    -0.38
     محفوظة
    -0.37
    POSITIVE LOGITS
     clients
    0.76
     Clients
    0.62
    clients
    0.58
    Clients
    0.56
     customers
    0.55
     offer
    0.54
    offer
    0.54
    offering
    0.51
     klanten
    0.50
     client
    0.49
    Activations Density 0.013%

    No Known Activations