© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 489
    Prev
    Next
    INDEX
    Explanations

    concepts related to diligence and the necessity of care in various contexts

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

    terms related to negligence and legal responsibility

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

    take reasonable care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    databind
    -0.55
    KommentareTeilen
    -0.49
    tableFuture
    -0.49
     LUMP
    -0.48
     moo
    -0.47
    MutableLiveData
    -0.47
    reactstrap
    -0.47
    phant
    -0.46
    tagHelperRunner
    -0.46
     layui
    -0.45
    POSITIVE LOGITS
     careful
    1.57
     meticulous
    1.54
     Careful
    1.42
     precautions
    1.34
     care
    1.30
     diligent
    1.28
     cuidad
    1.28
     sorgfäl
    1.27
    Careful
    1.25
     diligence
    1.24
    Activations Density 0.130%

    No Known Activations