© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 1389
    Prev
    Next
    INDEX
    Explanations

    the concept of "ideal" and its variations, along with references to "sweet" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    libatkan
    -0.50
    rawDesc
    -0.48
    DECREF
    -0.48
     propOrder
    -0.46
    SuspendLayout
    -0.45
     başlay
    -0.42
    bootstrapcdn
    -0.42
     NgModule
    -0.41
    RTSC
    -0.40
     livrer
    -0.40
    POSITIVE LOGITS
     sweet
    0.68
     Sweet
    0.65
     ideal
    0.64
    Sweet
    0.63
    sweet
    0.63
     extreme
    0.62
     monster
    0.60
     Monster
    0.57
     SWEET
    0.54
                        
    0.54
    Activations Density 0.251%

    No Known Activations