© 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. 22-GEMMASCOPE-RES-16K
    6. 11642
    Prev
    Next
    INDEX
    Explanations

    descriptions and announcements related to official openings and events

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

    Official events or ceremonies

    np_acts-logits-general · gemini-2.0-flash

    opening and dedications

    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
    ագրություններ
    -0.57
    angliski
    -0.56
     فريبيس
    -0.54
    closedir
    -0.54
     AssemblyTitle
    -0.50
    脚注の使い方
    -0.48
     IMDG
    -0.48
    lexikon
    -0.47
     referrerpolicy
    -0.47
     subido
    -0.46
    POSITIVE LOGITS
     opening
    1.46
     inauguration
    1.39
     launch
    1.36
     ribbon
    1.31
     Opening
    1.27
     inaugur
    1.25
    Opening
    1.24
     unveiling
    1.23
    opening
    1.21
     officially
    1.21
    Activations Density 0.196%

    No Known Activations