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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3879
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence boundaries

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

    Text after punctuation like periods, dashes

    np_acts-logits-general · gemini-2.0-flash

    indeed, fact, confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ượ
    -0.62
    rensa
    -0.54
    ?
    
    -0.50
    ?''
    -0.50
     Meanwhile
    -0.48
     للاسماء
    -0.48
     meanwhile
    -0.47
    PYX
    -0.47
    ❹
    -0.47
    ”?
    -0.47
    POSITIVE LOGITS
     indeed
    1.23
    indeed
    1.20
     infatti
    1.17
     anzi
    1.14
    Indeed
    1.10
     Indeed
    1.05
    むしろ
    0.98
     Bahkan
    0.94
    Bahkan
    0.93
     fact
    0.91
    Activations Density 0.280%

    No Known Activations