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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12597
    Prev
    Next
    INDEX
    Explanations

    words related to file compatibility and functionality in software applications

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

    File formats and extensions

    np_acts-logits-general · gemini-2.0-flash

    reading and importing file formats

    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
     Савезне
    -0.80
    ArgsConstructor
    -0.76
     useAppContext
    -0.75
     pageContext
    -0.69
    InjectMocks
    -0.68
     CreateTagHelper
    -0.66
    tagHelperRunner
    -0.64
    новниш
    -0.62
    AccessorTable
    -0.62
    pushFollow
    -0.61
    POSITIVE LOGITS
     *.
    1.02
     (.
    1.00
     .
    0.90
     files
    0.86
     zip
    0.85
     txt
    0.85
    (.
    0.83
     XML
    0.80
     CSV
    0.79
     `.
    0.79
    Activations Density 0.482%

    No Known Activations