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. 25-GEMMASCOPE-RES-16K
    6. 5780
    Prev
    Next
    INDEX
    Explanations

    references to penal colonies and their contexts

    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
     LS
    -1.07
     LC
    -1.04
     Ll
    -1.04
     LL
    -1.03
     LT
    -1.02
     LD
    -1.02
     LM
    -1.01
     LB
    -1.01
    LC
    -1.01
     LH
    -1.00
    POSITIVE LOGITS
    XtraReports
    0.39
     OMITBAD
    0.36
    cookieParser
    0.33
    ➯
    0.32
     AppComponent
    0.31
    )_/¯
    0.31
    pernicus
    0.30
     näytte
    0.30
    intios
    0.30
    ConverterFactory
    0.30
    Activations Density 8.873%

    No Known Activations