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. 16-GEMMASCOPE-RES-16K
    6. 1431
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to nuclear stopping and energy calculations in physics

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

    Relating physical quantities/units

    np_acts-logits-general · gemini-2.0-flash

    physical quantities and their ranges

    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
    stdafx
    -0.47
    strix
    -0.45
     Sil
    -0.43
     team
    -0.43
    ваку
    -0.41
    jkl
    -0.41
    idist
    -0.39
    তথ্যসূত্র
    -0.39
     West
    -0.39
     lounge
    -0.38
    POSITIVE LOGITS
     ainfi
    0.86
    
    0.80
    AxisAlignment
    0.73
     venons
    0.73
     plufieurs
    0.71
     ProductService
    0.70
     auroit
    0.69
     dignité
    0.69
    muito
    0.69
    RepeatedField
    0.68
    Activations Density 1.300%

    No Known Activations