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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 15897
    Prev
    Next
    INDEX
    Explanations

    terms related to financial and legal manipulations, including euphemisms for unethical practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.85
     GenerationType
    -0.81
    enderror
    -0.73
    HasForeignKey
    -0.72
     Мексичка
    -0.66
     constexpr
    -0.66
     كومونز
    -0.65
    InvalidProtocol
    -0.65
    énario
    -0.64
    存于互联网档案馆
    -0.64
    POSITIVE LOGITS
    いわゆる
    0.58
    aka
    0.51
     essentially
    0.47
    윗
    0.45
     plastique
    0.44
    AKA
    0.44
     pressure
    0.44
     qued
    0.43
     basically
    0.43
     popularly
    0.42
    Activations Density 0.421%

    No Known Activations