© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 501
    Prev
    Next
    INDEX
    Explanations

    elements related to positive performance and results in a creative context, particularly pertaining to baking and application development

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

    phrases expressing positive outcomes or successful results using the phrase "turned out" or "came out".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    IsMutable
    -0.75
    AndEndTag
    -0.67
     Italijanski
    -0.62
    AnimationsModule
    -0.62
     ویکی‌پدی
    -0.61
     kasarigan
    -0.56
     propOrder
    -0.56
    kháu
    -0.55
    Vidite
    -0.55
    CloseOperation
    -0.55
    POSITIVE LOGITS
     outcome
    1.08
     получилось
    1.04
     result
    0.94
     resulting
    0.89
    ออกมา
    0.84
     turned
    0.83
     получается
    0.83
     получится
    0.82
    result
    0.81
     Outcome
    0.81
    Activations Density 0.228%

    No Known Activations