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. 24-GEMMASCOPE-RES-16K
    6. 1046
    Prev
    Next
    INDEX
    Explanations

    elements related to celebrations and traditions in relationships

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

    Follows a quote attributed to a person

    np_acts-logits-general · gemini-2.0-flash

    insider continued

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.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
     quelquefois
    -0.53
     CommonModule
    -0.49
     ComVisible
    -0.48
     méri
    -0.47
     daß
    -0.47
     énergé
    -0.46
     skall
    -0.46
     Préférences
    -0.46
     normaux
    -0.45
     productivo
    -0.45
    POSITIVE LOGITS
     amid
    0.53
     slammed
    0.52
     reportedly
    0.51
     costar
    0.47
     onscreen
    0.47
     🥺
    0.46
     atop
    0.46
     boasted
    0.46
     mum
    0.46
     adorable
    0.46
    Activations Density 0.271%

    No Known Activations