© 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. 2-GEMMASCOPE-RES-16K
    11. 3904
    Prev
    Next
    INDEX
    Explanations

    numerical values that reflect state or status codes in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -1.10
     وتسجيلات
    -0.99
    tagHelperRunner
    -0.90
    Rüyada
    -0.87
    новниш
    -0.83
    الحياه
    -0.83
    setupUi
    -0.82
    ]--;
    -0.82
    TagMode
    -0.81
     fieldNum
    -0.81
    POSITIVE LOGITS
    0
    0.48
     *
    0.43
    Imagine
    0.42
     composed
    0.41
    تیب
    0.40
    ждений
    0.40
    2
    0.39
    liziert
    0.39
    мі
    0.36
    ждением
    0.36
    Activations Density 0.231%

    No Known Activations