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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 1692
    Prev
    Next
    INDEX
    Explanations

    words related to cuteness and endearing qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.30
     SwiftUI
    -1.08
    Tikang
    -0.96
    rungsseite
    -0.94
     Weyl
    -0.92
     ​​
    -0.86
    brainly
    -0.85
     Bourgoin
    -0.85
    ytale
    -0.82
     betweenstory
    -0.82
    POSITIVE LOGITS
    ly
    2.17
    LY
    1.28
    mente
    0.96
    fully
    0.89
    lyn
    0.83
    ably
    0.82
    lessly
    0.78
    ose
    0.78
    ására
    0.76
    cellular
    0.76
    Activations Density 0.240%

    No Known Activations