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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38054
    Prev
    Next
    INDEX
    Explanations

    financial metrics and data related to stock performance and dividends

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

    dividend percentage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onwards
    -0.66
     Amongst
    -0.59
     optimised
    -0.59
    Whilst
    -0.58
     amongst
    -0.57
     içerisinde
    -0.56
    ⓧ
    -0.55
     Whilst
    -0.54
     whilst
    -0.53
     functionalities
    -0.52
    POSITIVE LOGITS
    abestanden
    0.41
     téléph
    0.40
    SPJ
    0.39
    </caption>
    0.38
    tagHelperRunner
    0.38
    bootstrapcdn
    0.38
     EXHIBIT
    0.37
     diharapkan
    0.37
     REA
    0.37
     yyr
    0.36
    Activations Density 0.059%

    No Known Activations