© 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. 7-GEMMASCOPE-RES-16K
    6. 5712
    Prev
    Next
    INDEX
    Explanations

    terms related to improvement or augmentation, particularly in the context of experiences and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ips
    -0.76
    ia
    -0.71
     uParam
    -0.71
     Bieber
    -0.70
    мені
    -0.68
     PIL
    -0.65
     sayur
    -0.64
     Gries
    -0.64
     Miscell
    -0.64
    ก่
    -0.63
    POSITIVE LOGITS
    hancing
    1.33
     enhancements
    1.24
     enhancement
    1.15
     enhance
    1.14
     Enhance
    1.13
     Enhancement
    1.12
    hanced
    1.10
    enhance
    1.09
    enhanced
    1.08
    hances
    1.05
    Activations Density 0.120%

    No Known Activations