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. 12-GEMMASCOPE-RES-16K
    6. 1195
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreement and qualitative analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iprot
    -0.69
    EINVAL
    -0.59
     Parcelable
    -0.56
    DotNetBar
    -0.55
    CodeAttribute
    -0.55
    णी
    -0.53
    vinyl
    -0.52
     Tui
    -0.51
    EFAULT
    -0.51
     crdi
    -0.50
    POSITIVE LOGITS
     umum
    0.67
     basics
    0.67
     generale
    0.66
     geral
    0.61
     general
    0.61
     básico
    0.59
     basic
    0.58
    Geplaatst
    0.57
     generali
    0.56
    SourceChecksum
    0.56
    Activations Density 0.622%

    No Known Activations