© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1268
    Prev
    Next
    INDEX
    Explanations

    terms related to legal roles and corporate governance

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

    "In-house" or "internal" operations/production

    np_acts-logits-general · gemini-2.0-flash

    in house operations

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GEBURTSDATUM
    -0.90
    WebServlet
    -0.84
    ReusableCell
    -0.82
     otomatig
    -0.82
     doInBackground
    -0.79
    TagHelper
    -0.79
    WriteBarrier
    -0.78
     AttributeSet
    -0.77
    ContextHolder
    -0.74
     InputDecoration
    -0.72
    POSITIVE LOGITS
     internal
    1.82
     internally
    1.63
    internal
    1.52
     house
    1.45
    Internal
    1.40
     Internal
    1.38
     interno
    1.36
    house
    1.34
     interne
    1.25
     internes
    1.23
    Activations Density 0.245%

    No Known Activations