Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13808
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to computing and programming concepts

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

    Computer architecture and hardware design

    np_acts-logits-general · gemini-2.0-flash

    computer hardware design and simulation

    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
    脚注の使い方
    -0.77
    Personensuche
    -0.74
     pinulongan
    -0.71
     Shad
    -0.55
    GOTREF
    -0.55
     GUS
    -0.55
     Colli
    -0.54
     übers
    -0.53
    GUS
    -0.52
     inext
    -0.52
    POSITIVE LOGITS
     gates
    0.65
     gate
    0.64
     veril
    0.64
     synthesis
    0.63
     design
    0.57
     circuit
    0.56
     nets
    0.56
     CMOS
    0.55
     interconnect
    0.55
     Ver
    0.55
    Activations Density 0.518%

    No Known Activations