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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6441
    Prev
    Next
    INDEX
    Explanations

    financial advice and discussion regarding debt management

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

    Financial advice and retirement planning

    np_acts-logits-general · gemini-2.0-flash

    finance advisor retirement savings

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Taktlose
    -0.39
    chowa
    -0.38
    hbox
    -0.37
     виправивши
    -0.37
     lượt
    -0.36
     반
    -0.36
    期刊论文
    -0.35
     לר
    -0.34
     Futter
    -0.34
    enumi
    -0.34
    POSITIVE LOGITS
    Retirement
    0.65
     retirement
    0.64
     Retirement
    0.62
    retirement
    0.60
     CFP
    0.57
    Financial
    0.57
     Financial
    0.57
     financial
    0.56
     pleaſure
    0.54
     FINANCIAL
    0.54
    Activations Density 0.204%

    No Known Activations