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

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 14254
    Prev
    Next
    INDEX
    Explanations

    incidents involving arrests and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nadzieję
    -0.47
     every
    -0.45
     każdej
    -0.45
     vejo
    -0.43
     oczywiście
    -0.42
     význam
    -0.42
     fondament
    -0.42
     każde
    -0.42
     Vergangenheit
    -0.41
     hiszen
    -0.41
    POSITIVE LOGITS
     investigators
    1.26
     witnesses
    1.09
     authorities
    1.06
     Investigators
    1.00
    Investigators
    0.98
     officials
    0.94
     detectives
    0.92
     prosecutors
    0.91
    authorities
    0.85
    Witnesses
    0.85
    Activations Density 0.513%

    No Known Activations