© 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. 5718
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to data processing and exceptions in programming

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

    following prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    conditional logic

    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
    -0.85
    ThroughAttribute
    -0.84
     kasarigan
    -0.77
    TargetException
    -0.75
     estekak
    -0.74
    XMLSchema
    -0.72
    TypedDataSet
    -0.71
     defaultstate
    -0.69
    multer
    -0.64
    ValueStyle
    -0.63
    POSITIVE LOGITS
     subsequent
    0.79
     client
    0.74
     user
    0.71
     caller
    0.62
     runtime
    0.60
     Subsequent
    0.60
     users
    0.60
     clients
    0.60
    客户端
    0.59
     downstream
    0.59
    Activations Density 1.282%

    No Known Activations