© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9289
    Prev
    Next
    INDEX
    Explanations

    references to prison systems and inmate rights

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

    jails and prisons

    np_acts-logits-general · gemini-2.0-flash

    prison and jail context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aminya
    -0.44
     vetorial
    -0.41
     tradição
    -0.39
     đu
    -0.38
     typelib
    -0.37
    antMatchers
    -0.36
     exportación
    -0.36
    
    -0.36
     Italijanski
    -0.36
     espada
    -0.35
    POSITIVE LOGITS
     prison
    1.71
     Prison
    1.59
     prisoners
    1.52
     jail
    1.52
    prison
    1.51
     prisoner
    1.49
    Prison
    1.49
     inmate
    1.46
     inmates
    1.45
     prisons
    1.45
    Activations Density 1.206%

    No Known Activations