© 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. 11502
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of work-life balance and its implications

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

    Two things are related or connected

    np_acts-logits-general · gemini-2.0-flash

    two things are related

    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
    Chy
    -0.44
    ansing
    -0.44
    uruh
    -0.43
    Its
    -0.42
    twice
    -0.42
     próprio
    -0.42
    OIR
    -0.42
    Eddy
    -0.41
    ítico
    -0.40
    жев
    -0.40
    POSITIVE LOGITS
     mutually
    1.31
     interdependent
    1.28
     elkaar
    1.23
     saling
    1.19
     interrelated
    1.18
     interconnected
    1.14
     einander
    1.12
     birbir
    1.08
     overlapping
    1.08
     intertwined
    1.05
    Activations Density 1.184%

    No Known Activations