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. 12-GEMMASCOPE-RES-16K
    6. 2415
    Prev
    Next
    INDEX
    Explanations

    references to nighttime events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bơi
    -0.50
     fãs
    -0.43
     alça
    -0.41
    forbes
    -0.41
    balleur
    -0.40
    galus
    -0.40
     multer
    -0.40
     Fans
    -0.38
     Bona
    -0.38
    dozer
    -0.37
    POSITIVE LOGITS
    Night
    1.52
     Night
    1.48
     night
    1.47
     NIGHT
    1.40
    night
    1.32
     Nights
    1.22
     nights
    1.21
    Nights
    1.21
    NIGHT
    1.15
    nights
    1.09
    Activations Density 0.075%

    No Known Activations