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. 20-GEMMASCOPE-RES-131K
    6. 85681
    Prev
    Next
    INDEX
    Explanations

    instances of the word "obtain" in various forms and contexts

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

    the act of obtaining

    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
     $_(
    -0.76
     ſche
    -0.73
     queſta
    -0.71
    parsedMessage
    -0.68
     eventName
    -0.68
     ſte
    -0.66
     /*#__
    -0.65
    avascript
    -0.65
     newName
    -0.65
     purpoſe
    -0.65
    POSITIVE LOGITS
     obtain
    1.02
    Obtain
    0.93
     obtained
    0.93
    obtain
    0.92
     Obtain
    0.90
     obtenido
    0.85
    obtained
    0.79
     obtains
    0.77
     Obtained
    0.74
     obtenu
    0.73
    Activations Density 0.032%

    No Known Activations