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. 16-GEMMASCOPE-RES-16K
    6. 16052
    Prev
    Next
    INDEX
    Explanations

    quotes and spoken statements related to expressions of support and commitment

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

    Quoted speech introduction

    np_acts-logits-general · gemini-2.0-flash

    opening quotation marks

    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
     Frage
    -0.49
    ارة
    -0.47
    Frage
    -0.46
     question
    -0.44
    question
    -0.43
    اره
    -0.42
    Enllaços
    -0.42
    一応
    -0.42
    Verweise
    -0.42
     Vir
    -0.42
    POSITIVE LOGITS
    RegistryLite
    0.75
     protoimpl
    0.71
    Personendaten
    0.69
    UserScript
    0.68
    clable
    0.68
    Naissance
    0.67
     quæ
    0.61
    plotlib
    0.60
     Estou
    0.58
     ujednoznacz
    0.56
    Activations Density 0.068%

    No Known Activations