© 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. 8186
    Prev
    Next
    INDEX
    Explanations

    terms related to authentication and access management in computing environments

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

    software or web applications

    np_acts-logits-general · gemini-2.0-flash

    login, contact, license, resource, profile, verification

    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
     CreateTagHelper
    -0.77
     صوتيه
    -0.74
    StoryboardSegue
    -0.70
    IsContent
    -0.62
     незавершена
    -0.61
     becauſe
    -0.60
    BufferException
    -0.58
     externi
    -0.58
     perdon
    -0.58
     spagno
    -0.57
    POSITIVE LOGITS
     information
    0.88
     data
    0.78
     file
    0.74
     value
    0.73
     info
    0.73
     API
    0.73
     table
    0.72
     code
    0.71
     object
    0.70
     string
    0.69
    Activations Density 1.481%

    No Known Activations