© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3580
    Prev
    Next
    INDEX
    Explanations

    components and mechanisms related to mechanical systems and machinery

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

    technical components

    np_acts-logits-general · gemini-2.0-flash

    valve stem or heating element

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafiti
    -0.38
     нор
    -0.37
    értel
    -0.35
     duyg
    -0.35
    Достоинства
    -0.34
    weiterlesen
    -0.34
     confidential
    -0.34
    ทั่ว
    -0.33
     Ukrainian
    -0.33
     svensk
    -0.33
    POSITIVE LOGITS
    LookAnd
    0.63
     itself
    0.61
     MenuView
    0.60
     edges
    0.56
     '{@
    0.55
     Chwiliwch
    0.54
    FormTagHelper
    0.53
     OMITBAD
    0.53
    complexType
    0.52
     ब्रेकडाउन
    0.51
    Activations Density 0.765%

    No Known Activations