© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8598
    Prev
    Next
    INDEX
    Explanations

    phrases related to methods or processes used in research or technical descriptions

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

    "using" and equations

    np_acts-logits-general · gemini-2.0-flash

    using equations or methods

    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
    SharedDtor
    -0.68
     فريبيس
    -0.67
    ViewInit
    -0.66
     CreateTagHelper
    -0.62
     AppModule
    -0.60
     doInBackground
    -0.59
    IBAction
    -0.58
     صوتيه
    -0.57
     DMT
    -0.57
     onPostExecute
    -0.57
    POSITIVE LOGITS
     behulp
    0.75
    using
    0.72
     utilisant
    0.71
     Using
    0.66
     either
    0.66
     using
    0.64
     الاطلاع
    0.63
     memanfaatkan
    0.60
    either
    0.60
    Using
    0.57
    Activations Density 0.610%

    No Known Activations