© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 13850
    Prev
    Next
    INDEX
    Explanations

    instances of violence, injuries, and casualties in various contexts

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

    Suffering, death, or legal action

    np_acts-logits-general · gemini-2.0-flash

    actions affecting individuals

    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
    RegistryLite
    -0.82
     EconPapers
    -0.80
    protoimpl
    -0.76
    出版年
    -0.75
    Viitteet
    -0.74
     المعيارى
    -0.71
    IVEREF
    -0.71
    ]")]
    -0.70
    parsedMessage
    -0.64
     tartalomajánló
    -0.64
    POSITIVE LOGITS
     herself
    0.61
     himself
    0.57
     yourself
    0.57
     himſelf
    0.57
    himself
    0.53
     parha
    0.51
     yourselves
    0.51
     beſt
    0.50
    themselves
    0.50
     ourselves
    0.49
    Activations Density 0.172%

    No Known Activations