© 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. 24-GEMMASCOPE-RES-16K
    6. 13756
    Prev
    Next
    INDEX
    Explanations

    terms related to Azerbaijani cultural elements and music instruments

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

    Azerbaijani language and culture

    np_acts-logits-general · gemini-2.0-flash

    balaban

    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
    IndentedString
    -0.86
     snippetHide
    -0.74
     iconLine
    -0.70
    principalColumn
    -0.63
    IsContent
    -0.61
    twimg
    -0.61
    脚注の使い方
    -0.61
    msgTypes
    -0.58
    resave
    -0.57
    Chham
    -0.56
    POSITIVE LOGITS
     mə
    0.63
     və
    0.60
     tə
    0.59
     q
    0.56
    ə
    0.55
     şə
    0.52
     sə
    0.52
     ə
    0.52
     də
    0.50
     qi
    0.49
    Activations Density 0.039%

    No Known Activations