© 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. 16-GEMMASCOPE-RES-16K
    11. 9181
    Prev
    Next
    INDEX
    Explanations

    words related to research evaluation and treatment reporting

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

    Text followed by reporting words

    np_acts-logits-general · gemini-2.0-flash

    regarding terms in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.82
     ostavi
    -0.73
    ///</
    -0.72
     mergeFrom
    -0.71
     >=",
    -0.69
    ,$_
    -0.68
    ]){
    -0.68
    OGND
    -0.67
     oprot
    -0.67
    RunWith
    -0.67
    POSITIVE LOGITS
     riguardo
    0.69
     regarding
    0.69
     about
    0.65
     tentang
    0.64
     concerning
    0.61
     concernant
    0.59
     mengenai
    0.56
     acerca
    0.54
     privind
    0.53
    égard
    0.53
    Activations Density 0.882%

    No Known Activations