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. 74362
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession, accomplishment, or action related to the verb ‘have’

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

    you've + past action

    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
    ตัวเอง
    -0.42
     betrekking
    -0.41
     cuáles
    -0.41
     cuál
    -0.41
     Japão
    -0.40
     étrangère
    -0.40
     soort
    -0.39
     membuatnya
    -0.39
     extranjera
    -0.38
     Aufgrund
    -0.38
    POSITIVE LOGITS
    you
    0.68
    You
    0.66
     You
    0.66
     tetrach
    0.63
    AddTagHelper
    0.61
     الحره
    0.61
     Yous
    0.60
    your
    0.60
     YOU
    0.59
    ſelf
    0.59
    Activations Density 0.044%

    No Known Activations