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. 10-GEMMASCOPE-RES-16K
    6. 4670
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to food and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.23
     متعلقه
    -1.12
     GenerationType
    -0.91
     CreateTagHelper
    -0.86
     MonoBehaviour
    -0.83
     distanciation
    -0.82
     referenties
    -0.79
     Infórmanos
    -0.78
     Olivenöl
    -0.75
     ligiloj
    -0.75
    POSITIVE LOGITS
     enough
    0.94
    ness
    0.89
    enough
    0.87
     sexy
    0.79
     juicy
    0.79
     messy
    0.78
     spirited
    0.75
     elegant
    0.74
     cool
    0.73
     good
    0.73
    Activations Density 0.864%

    No Known Activations