© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 38882
    Prev
    Next
    INDEX
    Explanations

    instances of the word "resort" and its variations in the context of alternate actions or behaviors

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

    resort to / recourse to

    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
    ﹧
    -0.67
    enablog
    -0.66
     imagui
    -0.66
     verſch
    -0.66
     initComponents
    -0.65
     zwiſchen
    -0.65
     increí
    -0.64
     tartalo
    -0.64
    𝆺
    -0.63
    
    -0.63
    POSITIVE LOGITS
     resorted
    1.14
     resorting
    1.05
     recours
    0.95
     recurrir
    0.93
     resort
    0.85
     recourse
    0.72
    resort
    0.70
     resorts
    0.66
     Resort
    0.59
     recurso
    0.52
    Activations Density 0.016%

    No Known Activations