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. 2876
    Prev
    Next
    INDEX
    Explanations

    regulatory references concerning environmental impact assessments and compliance

    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
    migrationBuilder
    -0.58
    Personensuche
    -0.55
    ώ
    -0.51
     defaultstate
    -0.49
     Orrell
    -0.49
    ANTLR
    -0.48
    Insn
    -0.46
    TagHelper
    -0.45
    RenderAtEndOf
    -0.45
    ectoria
    -0.44
    POSITIVE LOGITS
     impacts
    1.12
     Impacts
    0.93
    Impacts
    0.90
     environmental
    0.88
     impact
    0.86
     mitigation
    0.86
    impact
    0.81
     impactos
    0.78
    Environmental
    0.78
     Environmental
    0.77
    Activations Density 0.142%

    No Known Activations