Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 1603
    Prev
    Next
    INDEX
    Explanations

    words associated with aspiration and inspiration in various contexts

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

    aspiring, inspiring, desiring

    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
    fortawesome
    -0.65
     Glue
    -0.55
    Glue
    -0.52
    hhhhhhhh
    -0.50
     toilette
    -0.49
    cancelButton
    -0.49
    Allo
    -0.49
     Telephone
    -0.48
     Automatically
    -0.48
    Dichloroethane
    -0.47
    POSITIVE LOGITS
     aspiring
    1.45
    iring
    0.60
     aspirants
    0.59
     aspire
    0.57
     budding
    0.52
     aspirant
    0.49
     jungen
    0.48
     wanna
    0.47
    Emerging
    0.47
    を目指す
    0.46
    Activations Density 0.004%

    No Known Activations