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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 90657
    Prev
    Next
    INDEX
    Explanations

    phrases related to making phone calls or contact

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

    phone numbers or services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.84
    PerformLayout
    -0.64
     queſta
    -0.63
     informée
    -0.62
    internalType
    -0.62
    enciaga
    -0.61
    
    -0.61
    IntoConstraints
    -0.60
    UIControlState
    -0.60
     erſt
    -0.60
    POSITIVE LOGITS
     call
    1.00
    Call
    0.98
    call
    0.97
     Call
    0.91
    CALL
    0.74
     calls
    0.71
     CALL
    0.70
    calls
    0.65
    Calls
    0.61
     telefónica
    0.61
    Activations Density 0.009%

    No Known Activations