© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1200
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to academic assignments and help

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

    Preceding tokens of "assignment" and "homework"

    np_acts-logits-general · gemini-2.0-flash

    homework assignment help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.69
    Kapcsolódó
    -0.57
     ©️
    -0.56
    $_['
    -0.56
    Expedia
    -0.55
    saraba
    -0.54
    setLayoutManager
    -0.54
    PhysRevLett
    -0.54
    省市镇
    -0.53
     Lath
    -0.50
    POSITIVE LOGITS
     assignments
    1.29
     assignment
    1.29
     homework
    1.20
     Assignments
    1.20
     Assignment
    1.10
    Assignment
    1.06
    assignment
    1.05
    homework
    1.02
     Homework
    1.01
    assignments
    0.98
    Activations Density 0.200%

    No Known Activations