© 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. 12235
    Prev
    Next
    INDEX
    Explanations

    terms relating to political systems and procedures, as well as mentions of medical conditions or terminologies

    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
    1978
    +0.14
    0.4%
    289
    +0.13
    0.4%
    50
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.14
    0.03
    324
    +0.13
    0.03
    1915
    +0.10
    0.04
    Negative Logits
     stockholm
    -0.89
     carrefour
    -0.86
     citoy
    -0.85
     lele
    -0.84
     germain
    -0.83
     javier
    -0.82
     embra
    -0.82
     budapest
    -0.81
     roberto
    -0.81
     fupp
    -0.81
    POSITIVE LOGITS
     system
    0.64
     region
    0.60
     environment
    0.59
     process
    0.58
     portion
    0.57
     scheme
    0.55
     program
    0.54
     sector
    0.54
     team
    0.53
     side
    0.53
    Activations Density 0.376%

    No Known Activations