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. 20-GEMMASCOPE-RES-16K
    6. 9423
    Prev
    Next
    INDEX
    Explanations

    references to financial concepts, particularly dividends and stock performance

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

    Followed by a letter or number

    np_acts-logits-general · gemini-2.0-flash

    financial and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.91
     AssemblyCulture
    -0.84
    WebServlet
    -0.80
    usercontent
    -0.80
    DeleteBehavior
    -0.79
    reactstrap
    -0.77
    GenerationType
    -0.69
    WebpackPlugin
    -0.68
    CompilerServices
    -0.67
     Registry
    -0.65
    POSITIVE LOGITS
     căr
    0.52
     besök
    0.46
    Step
    0.45
    Географија
    0.44
    CppMethod
    0.42
    مث
    0.41
     bawang
    0.41
    toEqual
    0.40
    foglal
    0.39
     woning
    0.39
    Activations Density 0.108%

    No Known Activations