© 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. 7124
    Prev
    Next
    INDEX
    Explanations

    specific programming or technical terms related to web development and data structures

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

    Tokens preceding specific nouns

    np_acts-logits-general · gemini-2.0-flash

    technical systems and quantities

    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
     ferons
    -0.40
     VizieR
    -0.38
     conosco
    -0.37
     Bài
    -0.37
    鼎
    -0.35
     AssemblyProduct
    -0.34
    Condiciones
    -0.34
    etcode
    -0.34
     artikelen
    -0.34
     equation
    -0.33
    POSITIVE LOGITS
    Personendaten
    0.74
    Personensuche
    0.64
    这位
    0.61
    這位
    0.61
    AutoField
    0.59
     lenker
    0.58
    ผู้
    0.58
     sender
    0.56
    MigrationBuilder
    0.53
     trader
    0.53
    Activations Density 1.672%

    No Known Activations