© 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. 11242
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal organizational structures and operations

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

    followed by "file," "files," or "organization"

    np_acts-logits-general · gemini-2.0-flash

    creating entities and content

    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
     undertaken
    -0.96
     emitted
    -0.91
     introduced
    -0.84
     issued
    -0.82
    introduced
    -0.81
     uttered
    -0.80
    taken
    -0.78
     acquired
    -0.77
     conducted
    -0.76
     collected
    -0.76
    POSITIVE LOGITS
     åt
    0.72
     capable
    0.69
     based
    0.65
     capables
    0.61
     using
    0.59
     ourselves
    0.58
    ึ้น
    0.57
     worthy
    0.54
     utilizzando
    0.53
     используя
    0.53
    Activations Density 0.804%

    No Known Activations