© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11131
    Prev
    Next
    INDEX
    Explanations

    phrases that convey depth or intensity of emotions and experiences

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

    "deep" or its variations

    np_acts-logits-general · gemini-2.0-flash

    concept of deepness

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     getItemCount
    -0.60
    
    -0.57
    bootstrapcdn
    -0.57
     queſta
    -0.57
    AddTagHelper
    -0.55
    Vidite
    -0.54
     '{@
    -0.53
    astify
    -0.53
    లాలు
    -0.53
    WebElementEntity
    -0.52
    POSITIVE LOGITS
     deep
    2.52
    deep
    2.27
     Deep
    2.25
    Deep
    2.23
     DEEP
    2.03
     deeply
    1.84
     deepest
    1.82
    DEEP
    1.81
     profundo
    1.78
     deeper
    1.77
    Activations Density 0.104%

    No Known Activations