© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6835
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to criminal charges and warrants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    warrants, fugitives, or pending charges

    np_acts-logits-general · gemini-2.0-flash

    warrant, wanted, pending, outstanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.76
    SequentialGroup
    -0.64
     InputDecoration
    -0.62
    fjspx
    -0.57
     transférez
    -0.55
     HttpClient
    -0.54
     behavi
    -0.54
    Geografi
    -0.53
     semula
    -0.52
     clicks
    -0.51
    POSITIVE LOGITS
     pending
    0.97
    pending
    0.68
     Pending
    0.67
    ecuzione
    0.65
     unresolved
    0.65
    Pending
    0.63
     CreateTagHelper
    0.62
     outstanding
    0.60
     recent
    0.58
     pendiente
    0.58
    Activations Density 0.467%

    No Known Activations