© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13280
    Prev
    Next
    INDEX
    Explanations

    references to "assets" and "facilities" in the context of finance or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thinking
    -0.47
    comprom
    -0.45
     consi
    -0.43
    Cosmo
    -0.43
    typeparam
    -0.42
    typeDefinition
    -0.41
     redu
    -0.41
     crist
    -0.41
     neg
    -0.41
     Cosmo
    -0.40
    POSITIVE LOGITS
     asset
    1.38
     Asset
    1.13
    asset
    1.06
     assets
    1.05
     facilities
    1.02
    Asset
    0.98
     Assets
    0.95
    ASSET
    0.92
     facility
    0.92
    facilities
    0.87
    Activations Density 0.136%

    No Known Activations