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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3101
    Prev
    Next
    INDEX
    Explanations

    financial terms related to property valuation and depreciation

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

    financial value

    np_acts-logits-general · gemini-2.0-flash

    financial value and its changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     kaarangay
    -0.48
    yonel
    -0.48
     Numerade
    -0.46
    featureID
    -0.45
     desaf
    -0.45
    DeleteBehavior
    -0.44
    öf
    -0.44
    ρίες
    -0.44
    lorette
    -0.44
    ovem
    -0.44
    POSITIVE LOGITS
     value
    2.42
    value
    2.09
     Value
    2.01
     valuation
    1.96
     VALUE
    1.93
    Value
    1.85
     valeur
    1.80
     valu
    1.80
     valuing
    1.79
     valore
    1.76
    Activations Density 0.236%

    No Known Activations