© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13327
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical terms related to conditions and definitions

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

    or characters followed by "V" or "VC"

    np_acts-logits-general · gemini-2.0-flash

    VC, VA, VE, VM, Vincent, VP, VR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.65
    apimachinery
    -0.59
    脚注の使い方
    -0.55
    scrapy
    -0.54
    Rhestr
    -0.50
    BASEPATH
    -0.49
    Tikang
    -0.47
    Erreferentziak
    -0.46
    anyahu
    -0.46
    Зноскі
    -0.45
    POSITIVE LOGITS
     VC
    1.27
     VA
    1.23
    VC
    1.20
     VE
    1.19
     VM
    1.17
     Vincent
    1.15
    VP
    1.15
     VP
    1.15
     VR
    1.15
    VR
    1.14
    Activations Density 1.254%

    No Known Activations