© 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. 4625
    Prev
    Next
    INDEX
    Explanations

    elements related to legal incidents and testimonies concerning violent crimes

    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
     ModelExpression
    -0.68
     midwives
    -0.67
    forChild
    -0.63
    TProtocol
    -0.63
     Profess
    -0.63
     veterinarians
    -0.61
    UserScript
    -0.61
     marketer
    -0.61
     clinician
    -0.61
    officer
    -0.61
    POSITIVE LOGITS
     recipients
    1.14
     recipient
    0.99
     victims
    0.95
     participants
    0.89
     beneficiaries
    0.87
    Recipients
    0.83
     complain
    0.81
     RECIP
    0.80
     victim
    0.80
     victimes
    0.80
    Activations Density 0.712%

    No Known Activations