© 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. 31-GEMMASCOPE-RES-16K
    6. 2148
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal penalties and financial rewards

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

    numerical quantities and measurements, particularly in contexts describing amounts, durations, speeds, sizes, or monetary values.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.66
    DebuggerStep
    -0.56
    ंदीखरीदारी
    -0.56
    enumii
    -0.54
    IsMutable
    -0.51
    parsedMessage
    -0.51
    ніципалі
    -0.50
    VYMaps
    -0.48
     Савезне
    -0.47
    IntOverflow
    -0.47
    POSITIVE LOGITS
     maximum
    1.24
     upto
    1.15
     max
    1.15
     jusqu
    1.11
    maximum
    1.09
    max
    1.08
     maksymal
    1.06
    最大
    1.05
     máximo
    1.05
    Maximum
    1.02
    Activations Density 0.563%

    No Known Activations