© 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. 23-GEMMASCOPE-RES-16K
    11. 9218
    Prev
    Next
    INDEX
    Explanations

    actions associated with violence and attacks against specific groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     difficulté
    -0.59
     difficultés
    -0.50
    KURZBESCHREIBUNG
    -0.49
    رایی
    -0.49
    itates
    -0.47
    textAppearance
    -0.47
     circonst
    -0.47
     concernés
    -0.46
     modalités
    -0.46
     compliqué
    -0.45
    POSITIVE LOGITS
     innocent
    1.54
    innocent
    1.33
     unsuspecting
    1.16
     innoc
    1.15
     inocente
    1.09
     defen
    1.07
    innoc
    1.05
     Innocent
    1.00
    Innoc
    0.98
     innocence
    0.94
    Activations Density 0.624%

    No Known Activations