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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14713
    Prev
    Next
    INDEX
    Explanations

    terms related to real estate transactions and selling properties

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

    Follows common words ("to", "the", "you")

    np_acts-logits-general · gemini-2.0-flash

    real estate or business dealings

    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
    tagHelperRunner
    -0.67
    httphttps
    -0.59
     فريبيس
    -0.53
     disambiguazione
    -0.53
    awtextra
    -0.50
    webElementXpaths
    -0.49
    AndEndTag
    -0.48
     Polskiego
    -0.47
    MigrationBuilder
    -0.47
     Chwiliwch
    -0.45
    POSITIVE LOGITS
    Gesture
    0.38
     sellers
    0.37
    sprozess
    0.36
     propertyName
    0.35
     timed
    0.35
    tape
    0.35
     stry
    0.35
     Executors
    0.34
    nexpected
    0.34
    jsii
    0.33
    Activations Density 0.053%

    No Known Activations