© 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. 24-GEMMASCOPE-RES-16K
    11. 1116
    Prev
    Next
    INDEX
    Explanations

    phrases or terms that indicate high quality or high value

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

    "high" preceding a characteristic

    np_acts-logits-general · gemini-2.0-flash

    high followed by specific descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opsis
    -0.48
     Cordero
    -0.45
    oplan
    -0.45
    amante
    -0.43
     Beren
    -0.43
    batter
    -0.42
    trn
    -0.42
    makebox
    -0.41
    anatomy
    -0.41
    GeneratedCode
    -0.40
    POSITIVE LOGITS
     High
    1.08
     high
    1.08
    High
    1.02
     HIGH
    1.01
    high
    0.96
    HIGH
    0.89
     highest
    0.76
     Low
    0.75
     Highest
    0.75
    Highest
    0.74
    Activations Density 0.224%

    No Known Activations