© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15098
    Prev
    Next
    INDEX
    Explanations

    concepts related to post-graduation plans and career readiness for students

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

    careers or future prospects

    np_acts-logits-general · gemini-2.0-flash

    careers and future professions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    TokenNameLBRACE
    -0.43
    pherds
    -0.40
    urion
    -0.39
     فريبيس
    -0.38
    plet
    -0.38
    Espèce
    -0.36
     incomplete
    -0.36
     ans
    -0.36
    astify
    -0.35
    otre
    -0.35
    POSITIVE LOGITS
    الإنجليزية
    0.56
     careers
    0.56
     carriera
    0.55
    bootstrapcdn
    0.54
     career
    0.54
    IVEREF
    0.51
    OrNil
    0.50
     carrière
    0.50
    career
    0.50
     emplois
    0.47
    Activations Density 0.149%

    No Known Activations