© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15787
    Prev
    Next
    INDEX
    Explanations

    references to victims and discussions surrounding victimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Granite
    -0.43
    lano
    -0.41
    paque
    -0.41
    isNotBlank
    -0.41
    WriteLiteral
    -0.40
     Cobalt
    -0.39
    fontaine
    -0.39
     flashy
    -0.39
    seamnă
    -0.38
    󠁮
    -0.38
    POSITIVE LOGITS
     victim
    2.00
     victims
    1.87
    victim
    1.82
     Victim
    1.78
    Victim
    1.76
     Victims
    1.66
     victime
    1.62
     victimes
    1.59
     vítima
    1.48
     vítimas
    1.45
    Activations Density 0.206%

    No Known Activations