© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5418
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions indicating actions or requests related to purchasing or obtaining items online

    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
    matchCondition
    -0.93
     препратки
    -0.91
    NOPQRST
    -0.91
    "];
    -0.90
    "]);
    -0.89
    "])
    -0.87
    الإنجليزية
    -0.86
    MLLoader
    -0.86
    )");
    -0.86
     nakalista
    -0.84
    POSITIVE LOGITS
    ↵
    0.52
    There
    0.43
     
    0.43
    He
    0.42
    1
    0.42
    In
    0.41
    A
    0.41
    2
    0.41
    勾
    0.39
    I
    0.38
    Activations Density 0.019%

    No Known Activations