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. 15-GEMMASCOPE-RES-16K
    6. 8702
    Prev
    Next
    INDEX
    Explanations

    organizational roles and positions within an academic or institutional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuppressLint
    -0.59
    Whilst
    -0.57
     Whilst
    -0.52
     realisation
    -0.51
     olay
    -0.51
     whilst
    -0.51
    Injectable
    -0.51
     realises
    -0.49
    лё
    -0.49
     honourable
    -0.49
    POSITIVE LOGITS
     campus
    1.06
     faculty
    1.05
    faculty
    0.91
     Faculty
    0.91
    Faculty
    0.87
    campus
    0.84
    Campus
    0.83
     CAMPUS
    0.81
     undergraduates
    0.78
     Campus
    0.76
    Activations Density 0.351%

    No Known Activations