© 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. 4124
    Prev
    Next
    INDEX
    Explanations

    terms related to economic sanctions and their implications

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

    preceding a verb

    np_acts-logits-general · gemini-2.0-flash

    critical and essential programs

    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
    Mej
    -0.33
    MouseAdapter
    -0.33
    Focus
    -0.33
    OpenHelper
    -0.32
     bershka
    -0.31
     invite
    -0.31
    balleur
    -0.31
     Apertura
    -0.31
    outputStream
    -0.31
     gig
    -0.31
    POSITIVE LOGITS
     vital
    1.06
     essential
    0.97
     vitales
    0.95
     essentielles
    0.94
     essentiels
    0.93
     crucial
    0.92
     vitale
    0.91
    essential
    0.91
     essentiel
    0.89
     essentielle
    0.89
    Activations Density 0.622%

    No Known Activations