© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14202
    Prev
    Next
    INDEX
    Explanations

    user interface interactions and commands related to buttons and menus

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

    Comes before a verb

    np_acts-logits-general · gemini-2.0-flash

    control commands

    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
    EndInit
    -0.56
     ControllerBase
    -0.51
     menghi
    -0.48
    tagext
    -0.44
    差
    -0.41
    ache
    -0.41
     ofreciendo
    -0.41
    fits
    -0.40
    σχ
    -0.38
     bulls
    -0.37
    POSITIVE LOGITS
    Filmografie
    0.78
    RegistryLite
    0.68
    reactstrap
    0.66
    épend
    0.66
    OGND
    0.66
    AddTagHelper
    0.66
    
    0.65
    effect
    0.65
     effect
    0.64
     Efq
    0.63
    Activations Density 0.598%

    No Known Activations