© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7841
    Prev
    Next
    INDEX
    Explanations

    references to budget cuts and financial constraints

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

    Actions related to cutting spending

    np_acts-logits-general · gemini-2.0-flash

    spending cuts

    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
    writeField
    -0.55
     INVENTION
    -0.49
    lutning
    -0.46
    Demografía
    -0.46
     &___
    -0.45
     actionMode
    -0.45
    apunov
    -0.43
    autoreleasepool
    -0.42
     xadrez
    -0.42
    }^{+\
    -0.42
    POSITIVE LOGITS
     cuts
    1.89
     cut
    1.81
     Cuts
    1.66
     cutting
    1.60
    cut
    1.56
    Cuts
    1.56
     Cut
    1.53
    cuts
    1.53
    Cutting
    1.51
     Cutting
    1.51
    Activations Density 0.379%

    No Known Activations