Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15228
    Prev
    Next
    INDEX
    Explanations

    references to specific cases or instances within a discussion or analysis

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

    "case" followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    in this case, this time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     éter
    -0.40
     faſt
    -0.39
     propOrder
    -0.38
     pinulongan
    -0.38
     continuamente
    -0.38
    Хьажоргаш
    -0.36
     BrowserModule
    -0.36
     organizacji
    -0.36
    Portály
    -0.36
     myſelf
    -0.36
    POSITIVE LOGITS
     diesmal
    0.79
    دانشنامهٔ
    0.65
     للمعارف
    0.59
    今回は
    0.56
    __":
    0.54
    AxisAlignment
    0.52
    case
    0.51
    __":
    
    0.50
    Ici
    0.49
    这次
    0.48
    Activations Density 0.331%

    No Known Activations