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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6606
    Prev
    Next
    INDEX
    Explanations

    indicators of budget cuts and financial constraints in a business context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.57
     &___
    -0.56
    writeField
    -0.55
    ствии
    -0.54
    arroll
    -0.48
     INVENTION
    -0.47
    }^{+\
    -0.47
     мѣ
    -0.46
    AllowAnonymous
    -0.46
    UVWXYZ
    -0.46
    POSITIVE LOGITS
     cuts
    1.93
     cut
    1.80
     Cuts
    1.69
     reductions
    1.61
     cutting
    1.57
    Cuts
    1.55
    cut
    1.53
    cuts
    1.53
     reduction
    1.49
     Cut
    1.48
    Activations Density 0.352%

    No Known Activations