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. 15-GEMMASCOPE-RES-16K
    6. 12576
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and symbols commonly found in technical or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mouseY
    -0.67
    setVerticalGroup
    -0.64
    gehalt
    -0.64
    centerY
    -0.61
     istrinya
    -0.60
    writeFieldEnd
    -0.60
    ifoli
    -0.56
     bezogen
    -0.55
    utives
    -0.54
     Italijanski
    -0.53
    POSITIVE LOGITS
    ExtendWith
    0.68
     متعلقه
    0.55
     <=",
    0.55
    ")));
    
    0.54
     ویکی‌پدیا
    0.51
    oa̍t
    0.49
    اعمال
    0.48
    Réalisation
    0.47
    writeField
    0.47
    RunWith
    0.47
    Activations Density 1.163%

    No Known Activations