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
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15682
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and special symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.69
    تقاوى
    -0.52
    ViewImports
    -0.50
    expandindo
    -0.45
     мәкал
    -0.45
    SpringBootTest
    -0.44
    TagMode
    -0.43
    SourceChecksum
    -0.42
    Geplaatst
    -0.42
    icrous
    -0.41
    POSITIVE LOGITS
     gesteld
    0.49
     wyda
    0.45
    Sitting
    0.44
    стероид
    0.42
     Auftritt
    0.41
     sentada
    0.41
     Sitting
    0.41
    qat
    0.41
    Later
    0.41
     sentado
    0.40
    Activations Density 0.399%

    No Known Activations