© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15622
    Prev
    Next
    INDEX
    Explanations

    phrases related to trust and family dynamics

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

    hip‑hop/rap content, especially lyrics and related metadata (artists, tracks, verses/choruses) with street/violent slang and production terms.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    hip-hop/rap lyrics, particularly dialogue and verses with AAVE (African American Vernacular English) features like dropped g's and slang.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    참고
    -0.41
     AssemblyCulture
    -0.40
    
    -0.39
    出版年
    -0.38
     CommonModule
    -0.36
    providedIn
    -0.36
     buchen
    -0.35
     inſ
    -0.35
     tranſ
    -0.35
     circo
    -0.34
    POSITIVE LOGITS
     rappers
    0.82
     rapper
    0.68
     niggas
    0.63
     hustle
    0.56
     fuck
    0.55
     rapping
    0.54
    ScreenState
    0.54
     mixtape
    0.54
     Rapper
    0.54
     haters
    0.54
    Activations Density 0.088%

    No Known Activations