© 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. 31272
    Prev
    Next
    INDEX
    Explanations

    phrases related to intended goals or purposes of actions, particularly through the use of the word "designed."

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

    designed to achieve purpose

    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
     verkoop
    -0.51
     respiración
    -0.41
     aérea
    -0.40
     henkil
    -0.40
     recev
    -0.40
     näky
    -0.40
     luzes
    -0.40
     sprzedaż
    -0.39
     vriend
    -0.38
     klant
    -0.38
    POSITIVE LOGITS
     aimed
    1.03
     designed
    0.77
     intended
    0.75
     Designed
    0.72
     aim
    0.72
     aims
    0.72
     aiming
    0.69
    旨在
    0.69
    Designed
    0.68
    fjspx
    0.66
    Activations Density 0.018%

    No Known Activations