© 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. 28-GEMMASCOPE-RES-16K
    11. 4274
    Prev
    Next
    INDEX
    Explanations

    terms related to decision-making based on comparisons and maximizing values

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

    Mathematical formulas, especially min/max

    np_acts-logits-general · gemini-2.0-flash

    max or min

    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
    parsedMessage
    -0.59
    VersionUID
    -0.47
    HomeAsUpEnabled
    -0.43
     ligiloj
    -0.43
    SpringBootTest
    -0.43
     Signalez
    -0.42
    Clik
    -0.42
     <<<<<<<<<<<<<<
    -0.42
    UnusedPrivate
    -0.42
     Lightboxes
    -0.41
    POSITIVE LOGITS
     highest
    1.48
     lowest
    1.34
     Highest
    1.32
    highest
    1.29
    Highest
    1.26
    lowest
    1.21
     Lowest
    1.18
     strongest
    1.16
    Lowest
    1.14
     best
    1.13
    Activations Density 0.600%

    No Known Activations