© 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. 7172
    Prev
    Next
    INDEX
    Explanations

    connections between various elements within a complex system or narrative

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

    "[Action] and then [another action]"

    np_acts-logits-general · gemini-2.0-flash

    and then

    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
    __(/*!
    -0.62
    expandindo
    -0.61
    værende
    -0.58
    ]--;
    -0.56
     дописавши
    -0.55
    didReceive
    -0.52
    memset
    -0.52
    nonatomic
    -0.52
    uç
    -0.52
    معلومات
    -0.51
    POSITIVE LOGITS
     then
    4.90
    then
    3.96
     Then
    3.88
    Then
    3.88
     THEN
    3.47
    THEN
    3.06
     entonces
    2.89
     dann
    2.85
     سپس
    2.83
     kemudian
    2.75
    Activations Density 2.645%

    No Known Activations