© 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. 18-GEMMASCOPE-RES-16K
    11. 14112
    Prev
    Next
    INDEX
    Explanations

    phrases related to justice and the deserving nature of individuals

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

    [Pronoun] deserved/deserves

    np_acts-logits-general · gemini-2.0-flash

    what is deserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gico
    -0.54
    picasso
    -0.52
    UAGES
    -0.50
    amic
    -0.46
     Tack
    -0.46
    Tack
    -0.45
    vito
    -0.44
     impractical
    -0.44
    ksis
    -0.43
    byter
    -0.43
    POSITIVE LOGITS
     deserved
    2.37
     deserve
    2.10
    deserved
    2.03
     deserving
    1.96
     deserves
    1.90
     merec
    1.65
     mérit
    1.62
     verdient
    1.55
     earned
    1.53
     rightfully
    1.40
    Activations Density 0.224%

    No Known Activations