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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 25-GEMMASCOPE-RES-16K
    6. 7990
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court cases and procedural aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.56
     EconPapers
    -0.52
     estekak
    -0.51
     Italijani
    -0.49
     MER
    -0.49
     विश्वसनीयता
    -0.48
     Kings
    -0.47
    enment
    -0.45
    nextProps
    -0.45
     communiquez
    -0.45
    POSITIVE LOGITS
    Geplaatst
    0.62
     AB
    0.53
    RTLD
    0.52
     Ab
    0.51
    Ab
    0.50
    NameInMap
    0.49
    Mo
    0.48
    EndContext
    0.48
    AB
    0.47
     ab
    0.47
    Activations Density 1.753%

    No Known Activations