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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 515
    Prev
    Next
    INDEX
    Explanations

    indicative phrases or terms related to customer service and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    TargetException
    -0.87
    awtextra
    -0.85
     '\\;'
    -0.69
     ExecuteAsync
    -0.68
    EXTERN
    -0.63
    __*/
    -0.58
     CreateTagHelper
    -0.56
    SequentialGroup
    -0.56
     BrowserModule
    -0.55
    InjectAttribute
    -0.55
    POSITIVE LOGITS
    GetObject
    0.51
    lite
    0.51
    webElementXpaths
    0.50
    NAL
    0.50
     Italijani
    0.50
    Style
    0.48
    olus
    0.47
    model
    0.47
    ņem
    0.47
     sick
    0.47
    Activations Density 0.122%

    No Known Activations