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. 21-GEMMASCOPE-RES-16K
    6. 7984
    Prev
    Next
    INDEX
    Explanations

    comments related to service quality and product satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.62
    LookAnd
    -0.60
    URLException
    -0.56
    tagPool
    -0.53
    __':
    
    -0.53
     Vikipedi
    -0.50
     يتيمه
    -0.50
     joão
    -0.50
     ✭✭
    -0.49
    complexType
    -0.48
    POSITIVE LOGITS
     klart
    0.43
     thoughtful
    0.40
    Reasonable
    0.37
    @[+][
    0.36
     reasonable
    0.35
    reasonable
    0.34
    rrggbb
    0.34
     sensibly
    0.34
     verkligen
    0.34
     gerçekten
    0.33
    Activations Density 0.128%

    No Known Activations