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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 8635
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their closing counterparts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.57
    er
    -0.48
    irot
    -0.48
    通販
    -0.47
    KommentareTeilen
    -0.46
     or
    -0.46
    времен
    -0.45
     strings
    -0.44
    IsInitialized
    -0.44
     life
    -0.44
    POSITIVE LOGITS
     дописавши
    1.12
    ("</
    1.08
    ."</
    1.04
     '</
    1.02
     "</
    1.02
    ngdoc
    1.00
    "</
    1.00
     }}"></
    1.00
    +'</
    0.94
    '</
    0.92
    Activations Density 0.047%

    No Known Activations