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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 434
    Prev
    Next
    INDEX
    Explanations

    programming-related function calls and variable assignments

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

    Code snippets or parts of code

    np_acts-logits-general · gemini-2.0-flash

    programmer code or specific terminology

    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
    DockStyle
    -0.75
    حياته
    -0.59
    Портал
    -0.59
    rzej
    -0.56
     beginnetje
    -0.55
    setVerticalGroup
    -0.55
     مشين
    -0.54
    הערות
    -0.54
    énario
    -0.54
    énéral
    -0.53
    POSITIVE LOGITS
    CloseOperation
    0.54
    [:]
    0.54
     value
    0.51
    Hentet
    0.51
     CreateTagHelper
    0.51
    🏿
    0.50
    APIView
    0.49
     jsPsych
    0.49
     []).
    0.49
    */].
    0.49
    Activations Density 0.102%

    No Known Activations