© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 6578
    Prev
    Next
    INDEX
    Explanations

    phrases that reference something as "referred to" or "known as."

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

    referred to as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.65
    AnchorStyles
    -0.59
    GTCX
    -0.49
    GeoNames
    -0.46
    ronpa
    -0.46
     JSTOR
    -0.46
    gebob
    -0.45
    Vidite
    -0.44
    ValueStyle
    -0.44
    DotNetBar
    -0.44
    POSITIVE LOGITS
     referred
    1.96
    referred
    1.61
     alluded
    0.91
     referenced
    0.83
     referral
    0.82
    ferred
    0.81
     REFER
    0.81
     mentioned
    0.80
     called
    0.78
     referido
    0.77
    Activations Density 0.011%

    No Known Activations