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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 77072
    Prev
    Next
    INDEX
    Explanations

    references to foreclosure processes and related legal terminology

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

    foreclosure and related financial terms

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SourceChecksum
    -0.56
    urlpatterns
    -0.48
    Moment
    -0.44
     createState
    -0.44
     smar
    -0.44
    GEBURTSDATUM
    -0.42
     mandar
    -0.42
     jenny
    -0.41
    resizingMask
    -0.40
    SerializedName
    -0.40
    POSITIVE LOGITS
     foreclosure
    1.80
     bankruptcy
    0.80
     Bankruptcy
    0.76
    closures
    0.71
     eviction
    0.68
     forfeiture
    0.63
     mortgages
    0.58
     refinancing
    0.57
    oprecipitation
    0.57
     liquidation
    0.56
    Activations Density 0.005%

    No Known Activations