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. 24-GEMMASCOPE-RES-16K
    6. 4510
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or formatting elements related to structure

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and code structure

    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
     contextLoads
    -0.65
     utafitiHapana
    -0.59
     مشين
    -0.58
    BeginContext
    -0.58
    centerY
    -0.56
     fusca
    -0.55
    reiten
    -0.54
    طقة
    -0.53
     demain
    -0.52
    בודה
    -0.52
    POSITIVE LOGITS
    "},
    
    0.43
    '},
    
    0.41
    )]);
    0.39
     mola
    0.39
    }}],
    0.39
     Barbuda
    0.38
    த
    0.38
     pooh
    0.38
     chihuahua
    0.38
     للمعارف
    0.38
    Activations Density 0.040%

    No Known Activations