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. 38-GEMMASCOPE-RES-16K
    6. 15087
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms used in advanced physics equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.69
     EconPapers
    -0.67
    aarrggbb
    -0.61
     snippetHide
    -0.56
    ClientSize
    -0.54
    قایناقلار
    -0.51
    OCCURRED
    -0.50
     @"/
    -0.50
     Administrativna
    -0.49
    /**
    -0.49
    POSITIVE LOGITS
     weak
    0.67
     weakness
    0.60
    weak
    0.59
     Weak
    0.52
    Weak
    0.51
     weaknesses
    0.51
     Weakness
    0.50
    弱
    0.48
     weaken
    0.48
     weakened
    0.48
    Activations Density 1.057%

    No Known Activations