© 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. 7464
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to excitations and transitions in physical systems

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

    after physical or mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    generated photon

    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
     AssemblyCompany
    -0.48
    MethodManager
    -0.42
     definition
    -0.42
     newOwner
    -0.41
    启
    -0.38
    ServletConfig
    -0.38
    definition
    -0.37
     konfer
    -0.37
     grid
    -0.36
     للاسماء
    -0.36
    POSITIVE LOGITS
     resonances
    0.51
     Meksiku
    0.46
     tangga
    0.45
     émotions
    0.44
     radiative
    0.44
     emitting
    0.43
     émission
    0.43
    łaszcza
    0.43
    adaptiveStyles
    0.42
     Efq
    0.42
    Activations Density 0.964%

    No Known Activations