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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 13926
    Prev
    Next
    INDEX
    Explanations

    terms related to career development and planning

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

    career choice and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    밌
    -0.45
    nitzer
    -0.44
     small
    -0.43
    tiglie
    -0.42
     mosque
    -0.41
     suspiciously
    -0.40
     bandage
    -0.39
    culously
    -0.39
     Mite
    -0.39
     Lordships
    -0.39
    POSITIVE LOGITS
     career
    1.17
    Career
    1.13
     careers
    1.08
    career
    1.07
     Career
    1.05
     CAREER
    0.97
    Careers
    0.95
     Careers
    0.92
    CAREER
    0.91
     carriera
    0.81
    Activations Density 0.007%

    No Known Activations