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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12703
    Prev
    Next
    INDEX
    Explanations

    financial advice and guidance related to debt management and personal finance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.61
     للاسماء
    -0.57
     المعيارى
    -0.55
     WaitForSeconds
    -0.52
     yyj
    -0.51
     صوتيه
    -0.49
    #
    -0.49
    UrlEncoded
    -0.48
     aDecoder
    -0.47
    ције
    -0.46
    POSITIVE LOGITS
     advisors
    1.19
     advisor
    1.15
     Financial
    1.13
     financial
    1.12
    Advis
    1.11
     advisers
    1.10
     adviser
    1.07
     Advisors
    1.06
    Financial
    1.05
     Advisor
    1.02
    Activations Density 0.139%

    No Known Activations