© 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. 125245
    Prev
    Next
    INDEX
    Explanations

    concepts of satisfaction and fulfilling experiences

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

    satisfaction and fulfillment

    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
     esternos
    -0.44
    tvguidetime
    -0.37
    createElement
    -0.37
    IndentedString
    -0.37
    Nuorodos
    -0.37
    ibase
    -0.36
    alahan
    -0.36
     πρό
    -0.35
     Penggunaan
    -0.34
     Derechos
    -0.34
    POSITIVE LOGITS
     satisfying
    1.24
    satis
    0.88
     Satis
    0.84
    Satis
    0.82
     satisf
    0.74
     gratifying
    0.70
     satisfies
    0.68
     fulfilling
    0.68
     satisfied
    0.65
     satisfa
    0.65
    Activations Density 0.007%

    No Known Activations