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
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5799
    Prev
    Next
    INDEX
    Explanations

    references to tax-related topics and government policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.48
     intStringLen
    -0.47
     liggen
    -0.45
    usercontent
    -0.44
    andExpect
    -0.39
    protoimpl
    -0.38
    ectoria
    -0.36
    AccessorTable
    -0.35
    Rptr
    -0.34
    ᅠ
    -0.34
    POSITIVE LOGITS
     subsidies
    1.32
     subsidy
    1.27
     grants
    1.22
     subsid
    1.11
    subsid
    1.07
     Subsid
    1.06
     grant
    1.05
     assistance
    1.05
     schemes
    0.99
     Grants
    0.98
    Activations Density 0.423%

    No Known Activations