© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2012
    Prev
    Next
    INDEX
    Explanations

    surveillance-related terms and security measures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    946
    +0.13
    0.4%
    690
    +0.10
    0.3%
    678
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.13
    0.05
    240
    +0.10
    0.03
    426
    +0.10
    0.03
    Negative Logits
     Mlle
    -0.83
     Souha
    -0.77
     marte
    -0.75
     Să
    -0.74
     ugg
    -0.73
     vache
    -0.70
     Că
    -0.68
     lola
    -0.68
     reluct
    -0.68
     lapin
    -0.67
    POSITIVE LOGITS
     surveillance
    0.88
     cameras
    0.81
     monitoring
    0.81
     CCTV
    0.77
     Surveillance
    0.75
    veillance
    0.73
     monitor
    0.69
     camera
    0.69
     monitors
    0.69
     Monitoring
    0.68
    Activations Density 0.461%

    No Known Activations