Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12120
    Prev
    Next
    INDEX
    Explanations

    positive feedback about customer service and experiences

    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
    UnsafeEnabled
    -0.41
    InteropServices
    -0.38
    Parcelize
    -0.38
    serviceWorker
    -0.35
    webElementGuid
    -0.34
    Unless
    -0.34
    [...,
    -0.34
    complexType
    -0.33
     dependence
    -0.33
    ]){
    
    -0.33
    POSITIVE LOGITS
     patiently
    0.50
    GTCX
    0.49
     يتيمه
    0.49
    +#+#
    0.48
     gynhyrchwyd
    0.48
    Gambas
    0.47
    出版年
    0.46
     nakalista
    0.45
     kysy
    0.44
    erapeutics
    0.44
    Activations Density 0.148%

    No Known Activations