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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7217
    Prev
    Next
    INDEX
    Explanations

    instances of legal or official terms related to penalties and charges

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

    Attribution or source reporting

    np_acts-logits-general · gemini-2.0-flash

    according to sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Says
    -0.58
    umumkan
    -0.58
    TestMethod
    -0.56
     Says
    -0.55
     defaultstate
    -0.55
    yorlar
    -0.53
     Describes
    -0.52
    )++;
    -0.51
     Sadly
    -0.51
     DEFENDANT
    -0.51
    POSITIVE LOGITS
     according
    1.12
     officials
    1.06
     experts
    0.79
     sources
    0.76
    according
    0.76
     menurut
    0.75
     executives
    0.73
     authorities
    0.70
     analysts
    0.70
     organizers
    0.66
    Activations Density 0.162%

    No Known Activations