© 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. 12-GEMMASCOPE-RES-16K
    6. 6635
    Prev
    Next
    INDEX
    Explanations

    terms related to morality and ethics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Silvio
    -0.81
     Guilherme
    -0.80
     Dada
    -0.77
     meninos
    -0.77
     Madeira
    -0.76
     Padua
    -0.75
     Madagascar
    -0.75
     valentin
    -0.75
    >>(
    -0.75
     Appleton
    -0.75
    POSITIVE LOGITS
     Morales
    1.16
     Mor
    1.13
    Mor
    1.03
     MOR
    0.96
     mor
    0.90
     morales
    0.85
    mor
    0.82
     Mortimer
    0.80
     Moran
    0.80
    MOR
    0.79
    Activations Density 0.216%

    No Known Activations