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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 2302
    Prev
    Next
    INDEX
    Explanations

    occurrences of structural or formatting elements in code or data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plus
    -0.50
     davon
    -0.50
     S
    -0.48
    ardless
    -0.47
    乍
    -0.46
     G
    -0.46
     Co
    -0.46
     et
    -0.45
    makedirs
    -0.45
    我还是
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    0.94
    GEBURTSDATUM
    0.87
    verwijspagina
    0.85
    enumi
    0.84
    存于互联网档案馆
    0.84
    []{
    0.84
    ]={
    0.83
    +#+#
    0.82
     resourceCulture
    0.80
     auroit
    0.80
    Activations Density 0.127%

    No Known Activations