© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2699
    Prev
    Next
    INDEX
    Explanations

    terms related to the impartiality and integrity of the judiciary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.72
    IVEREF
    -0.70
    makeConstraints
    -0.55
    djangoproject
    -0.55
     Италијани
    -0.54
    MessageOf
    -0.51
    міністра
    -0.51
    detectChanges
    -0.51
    StackNavigator
    -0.50
    日閲覧
    -0.49
    POSITIVE LOGITS
     impartial
    1.93
     unbiased
    1.91
     neutral
    1.80
     impartiality
    1.64
     neutrality
    1.59
     objectivity
    1.57
    neutral
    1.53
     neutre
    1.45
     neutr
    1.45
     Neutral
    1.44
    Activations Density 0.330%

    No Known Activations