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. 9-GEMMASCOPE-RES-16K
    6. 15326
    Prev
    Next
    INDEX
    Explanations

    quantitative data regarding counts and estimates related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.59
    ymce
    -0.57
     onOptions
    -0.54
    RoutingModule
    -0.54
     None
    -0.54
     fuite
    -0.53
    AnchorStyles
    -0.52
     Nusa
    -0.52
    hasMoreElements
    -0.52
    RouterModule
    -0.51
    POSITIVE LOGITS
    Millions
    1.05
     millions
    0.89
     Millions
    0.87
    millions
    0.84
     millones
    0.82
     milliards
    0.81
     billions
    0.79
    Thousands
    0.77
     milhões
    0.76
    thousands
    0.76
    Activations Density 0.415%

    No Known Activations