© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 23063
    Prev
    Next
    INDEX
    Explanations

    phrases that imply requests or pleas for attention

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

    quantifier or finality phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases that emphasize brevity or limited quantity/time, especially “one more/last” or “just a little/for a few minutes”-type remarks.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     contextLoads
    -0.48
    省市镇
    -0.47
     calendriers
    -0.44
    chainId
    -0.42
    VersionUID
    -0.41
    utilisons
    -0.41
    دانشنامهٔ
    -0.40
     defStyleAttr
    -0.39
    hood
    -0.39
    تقاوى
    -0.38
    POSITIVE LOGITS
    Brief
    0.49
     brief
    0.43
    pert
    0.43
     iprot
    0.41
     <<<<<<<<<<<<<<
    0.41
    BSITE
    0.41
    ِّف
    0.41
    rxjs
    0.40
     ultimi
    0.40
    WebpackPlugin
    0.40
    Activations Density 0.077%

    No Known Activations