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. 5-GEMMASCOPE-RES-16K
    6. 1432
    Prev
    Next
    INDEX
    Explanations

    questions directed at the reader that require their opinion or input

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.68
     InputDecoration
    -0.64
     CreateTagHelper
    -0.64
    exitRule
    -0.61
     SqlCommand
    -0.60
    FormTagHelper
    -0.59
     BorderRadius
    -0.58
     Alha
    -0.58
    ίναι
    -0.58
    versiti
    -0.58
    POSITIVE LOGITS
    DropColumn
    0.58
     newOwner
    0.47
     your
    0.46
    밖
    0.46
     you
    0.45
    udnio
    0.44
    utri
    0.44
    うら
    0.44
     latent
    0.43
    SpringRunner
    0.43
    Activations Density 0.102%

    No Known Activations