© 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. 1-GEMMASCOPE-RES-16K
    11. 8283
    Prev
    Next
    INDEX
    Explanations

    negative descriptors related to poor quality or moral shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    énario
    -0.77
    prnewswire
    -0.60
     censi
    -0.56
    BeginContext
    -0.53
     ISNI
    -0.53
     část
    -0.52
    izzi
    -0.52
    Kariera
    -0.51
    ثيق
    -0.50
    SuppressLint
    -0.50
    POSITIVE LOGITS
     bad
    4.27
    bad
    4.03
    Bad
    3.92
     Bad
    3.88
     BAD
    3.50
    BAD
    3.16
     mauvaise
    2.19
     schlechte
    2.08
     mauvais
    2.04
     badly
    1.99
    Activations Density 0.052%

    No Known Activations