© 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. 22-GEMMASCOPE-RES-16K
    11. 12751
    Prev
    Next
    INDEX
    Explanations

    code snippets related to audio processing and client libraries

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

    Class names or object instances

    np_acts-logits-general · gemini-2.0-flash

    object instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.95
    transQ
    -0.77
    HomeAsUpEnabled
    -0.77
    SaveChangesAsync
    -0.76
    Hochspringen
    -0.73
    verifyException
    -0.71
    جمعیت
    -0.70
     betweenstory
    -0.70
     समीक्षाओं
    -0.69
    ➟
    -0.68
    POSITIVE LOGITS
     object
    1.27
     instance
    1.21
    对象
    1.11
     객체
    0.99
     objects
    0.99
     class
    0.99
     objeto
    0.99
    instance
    0.98
    object
    0.93
     instances
    0.89
    Activations Density 0.711%

    No Known Activations