Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 1356
    Prev
    Next
    INDEX
    Explanations

    references to data management and interaction

    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
    gypti
    -0.62
    bootstrapcdn
    -0.62
    ]),
    
    -0.61
    defineProperty
    -0.60
    @[+][
    -0.58
    rrggbb
    -0.57
     مرئيه
    -0.57
     alia
    -0.54
    mitian
    -0.54
    addPreferredGap
    -0.53
    POSITIVE LOGITS
    +#+#
    0.84
     Catawiki
    0.78
    PropertyChanging
    0.64
    IndentedString
    0.61
    ControllerAdvice
    0.54
    SizeF
    0.53
     Савез
    0.52
     accordingly
    0.52
    Datuak
    0.51
    elesai
    0.50
    Activations Density 0.532%

    No Known Activations