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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2127
    Prev
    Next
    INDEX
    Explanations

    specific legal terms and phrases related to criminal activities and legal proceedings

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

    mentions of criminal activities or legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    терак
    -0.58
     EconPapers
    -0.56
    zitter
    -0.54
    AccessorTable
    -0.51
    crites
    -0.50
    InputBorder
    -0.48
     prochains
    -0.48
     varm
    -0.47
    tainable
    -0.47
    المشاركات
    -0.46
    POSITIVE LOGITS
     aged
    0.86
     unemployed
    0.82
     âgé
    0.82
     berusia
    0.76
     age
    0.73
     identified
    0.72
     pleaded
    0.70
     Identified
    0.68
     identificado
    0.68
     pregi
    0.68
    Activations Density 0.334%

    No Known Activations