Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1594
    Prev
    Next
    INDEX
    Explanations

    numeric values and their relationships in a complex data structure

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

    Followed by a colon and a number

    np_acts-logits-general · gemini-2.0-flash

    timestamps and legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.93
    SequentialGroup
    -0.66
    SPATH
    -0.65
     nahilalakip
    -0.63
    клопе
    -0.62
    AnchorStyles
    -0.60
    
    -0.59
    WriteBarrier
    -0.57
     NavController
    -0.55
     DJI
    -0.55
    POSITIVE LOGITS
    intios
    0.53
    цепт
    0.52
    NewUrlParser
    0.51
     utafitiHapana
    0.51
    Parcelize
    0.50
    iola
    0.49
    velocityX
    0.46
     Vorder
    0.45
    Teraz
    0.45
     soggiorno
    0.45
    Activations Density 1.029%

    No Known Activations