© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8103
    Prev
    Next
    INDEX
    Explanations

    terms related to analytical solutions and mathematical formulations

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

    phrases related to solving problems analytically in scientific or mathematical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    WebServlet
    -0.71
     <=",
    -0.67
    Personensuche
    -0.65
     protoimpl
    -0.64
     Normdatei
    -0.64
    Personendaten
    -0.63
    MemoryWarning
    -0.62
     Numerade
    -0.62
     незавершена
    -0.62
    styleType
    -0.61
    POSITIVE LOGITS
     analysis
    0.42
     derived
    0.38
     derivation
    0.38
     simplified
    0.38
     calculation
    0.38
     derive
    0.36
     study
    0.33
     calculate
    0.32
     deriving
    0.31
     computation
    0.31
    Activations Density 1.162%

    No Known Activations