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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 11517
    Prev
    Next
    INDEX
    Explanations

    instructions related to home cooling and energy efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lumia
    -0.55
     MERCHANTABILITY
    -0.51
     Mifflin
    -0.50
    czech
    -0.46
    pulo
    -0.46
     veci
    -0.46
     الحره
    -0.44
     gawas
    -0.44
    dope
    -0.43
    Weaknesses
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.79
    addCriterion
    0.77
    __(/*!
    0.77
    MemoryWarning
    0.77
    GrantedAuthority
    0.76
    GraphicsUnit
    0.75
     HasFactory
    0.72
    ⓧ
    0.71
    expandindo
    0.67
    randomUUID
    0.67
    Activations Density 0.186%

    No Known Activations