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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 45627
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal opinions or feelings about decisions or actions

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

    maybe or perhaps

    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
    estacks
    -0.39
     تانيه
    -0.36
    ViewFeatures
    -0.36
    Referències
    -0.34
    ValueGeneration
    -0.33
     largely
    -0.33
     disponibilités
    -0.33
    पया
    -0.32
     autorytatywna
    -0.32
    ፩
    -0.32
    POSITIVE LOGITS
     maybe
    0.60
     Maybe
    0.57
    Maybe
    0.56
    Perhaps
    0.54
     Perhaps
    0.54
    maybe
    0.54
    perhaps
    0.54
     kanske
    0.51
     perhaps
    0.50
     kanskje
    0.49
    Activations Density 0.047%

    No Known Activations