© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8356
    Prev
    Next
    INDEX
    Explanations

    occurrences of the "::" symbol, commonly used in programming to indicate namespace or scope resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.84
    tagHelperRunner
    -0.74
     transfieras
    -0.73
     ſei
    -0.73
     NSCoder
    -0.68
    irvana
    -0.68
     ſind
    -0.68
     faſt
    -0.67
     ſich
    -0.67
    verifyException
    -0.66
    POSITIVE LOGITS
    ::
    3.28
     ::
    2.08
    >::
    1.70
    :::
    1.61
    ::$
    1.59
    ::_
    1.59
    ::::
    1.49
    ::{
    1.41
    (::
    1.28
    ::~
    1.27
    Activations Density 0.070%

    No Known Activations