© 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. 15-GEMMASCOPE-RES-16K
    11. 4481
    Prev
    Next
    INDEX
    Explanations

    concepts related to safety, efficiency, and cost reduction in technical 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
     صوتيه
    -0.76
    mybatisplus
    -0.74
    oredCriteria
    -0.70
     defaultstate
    -0.68
    Filmografie
    -0.67
    RegistryLite
    -0.65
    antaranya
    -0.64
    =$((
    -0.64
     تضيفلها
    -0.63
    شهاد
    -0.61
    POSITIVE LOGITS
     because
    0.53
     karena
    0.52
     futuros
    0.51
    ärna
    0.48
    انه
    0.48
     Volkes
    0.47
     miatt
    0.46
    omock
    0.45
    hdysval
    0.44
     InputDecoration
    0.44
    Activations Density 0.431%

    No Known Activations