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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2919
    Prev
    Next
    INDEX
    Explanations

    terms related to the cancellation and rescinding of events or agreements

    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
    жер
    -0.45
     wear
    -0.43
    arg
    -0.42
     Liar
    -0.41
     Bourgeois
    -0.41
    курен
    -0.40
    pm
    -0.40
    ücken
    -0.40
    愫
    -0.40
    \_\_
    -0.39
    POSITIVE LOGITS
     Wikimedijinoj
    1.04
     onCancelled
    0.87
    脚注の使い方
    0.86
    "?>
    0.79
     doInBackground
    0.78
     CANCEL
    0.75
    Extinguishing
    0.75
    expandindo
    0.74
     cancelled
    0.73
    NameInMap
    0.73
    Activations Density 0.426%

    No Known Activations