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. 6815
    Prev
    Next
    INDEX
    Explanations

    snippets or code examples related to programming

    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
    GraphicsUnit
    -0.81
     canst
    -0.66
    }))
    
    -0.65
     ComVisible
    -0.65
    crollView
    -0.65
    GenerationType
    -0.64
     onBackPressed
    -0.64
     terecht
    -0.61
    ApiModelProperty
    -0.61
     endregion
    -0.60
    POSITIVE LOGITS
     example
    1.82
     sample
    1.62
     demo
    1.50
     Example
    1.50
     examples
    1.49
    example
    1.48
    Example
    1.47
     demonstration
    1.45
    Sample
    1.34
     Sample
    1.34
    Activations Density 0.729%

    No Known Activations