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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8594
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and references related to cellular biology and genetics

    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
    CreateMap
    -0.91
     sovra
    -0.69
    mathscr
    -0.68
     Jennie
    -0.66
    =&
    -0.66
     Alli
    -0.65
    سكرية
    -0.65
    Swar
    -0.64
     McPherson
    -0.64
     ngh
    -0.63
    POSITIVE LOGITS
     оригіналу
    0.96
     doInBackground
    0.92
    Portail
    0.85
    runApp
    0.83
    Rhythm
    0.82
     Damon
    0.82
    miral
    0.81
    erequisites
    0.80
     millet
    0.80
    hetics
    0.79
    Activations Density 2.077%

    No Known Activations