© 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. 15-GEMMASCOPE-RES-16K
    6. 2686
    Prev
    Next
    INDEX
    Explanations

    references to food and family gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     classifica
    -0.54
     UPON
    -0.53
    tagext
    -0.52
     Mixture
    -0.52
     corren
    -0.52
     momen
    -0.48
    damen
    -0.47
     réfugi
    -0.47
     corresponden
    -0.47
     congé
    -0.47
    POSITIVE LOGITS
     ExecuteAsync
    0.68
     NSError
    0.67
    HasForeignKey
    0.67
    esez
    0.65
     ostavi
    0.55
    SharedCtor
    0.54
    /******/
    0.54
     препратки
    0.54
     հղումներ
    0.53
     raise
    0.53
    Activations Density 0.398%

    No Known Activations