© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2573
    Prev
    Next
    INDEX
    Explanations

    Turkish terms and phrases related to music and cultural practices

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

    Codes or references (e.g., @bizimMDPI)

    np_acts-logits-general · gemini-2.0-flash

    good or plural Turkish suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.03
     للمعارف
    -0.78
    GEBURTSDATUM
    -0.77
    KommentareTeilen
    -0.76
    SharedDtor
    -0.76
    
    -0.75
    PerformLayout
    -0.75
    IVEREF
    -0.75
     صوتيه
    -0.75
    AddTagHelper
    -0.74
    POSITIVE LOGITS
    lik
    0.45
    li
    0.42
    lar
    0.42
     nok
    0.40
    lent
    0.39
    less
    0.39
    luk
    0.38
    tagez
    0.38
    ler
    0.38
    lize
    0.37
    Activations Density 0.032%

    No Known Activations