© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12197
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical and cultural heritage sites, government and political topics, as well as technological and digital concepts

    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
    1870
    +0.16
    0.5%
    1385
    +0.15
    0.5%
    738
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.16
    0.06
    280
    +0.15
    0.06
    74
    +0.10
    0.04
    Negative Logits
     unden
    -1.98
     reluct
    -1.94
     depic
    -1.93
     scrat
    -1.92
     volunte
    -1.91
     increa
    -1.90
     affor
    -1.90
     inev
    -1.89
     accla
    -1.88
     perfet
    -1.87
    POSITIVE LOGITS
     items
    0.88
    .
    0.82
     practices
    0.81
     options
    0.81
     units
    0.79
     activities
    0.79
     projects
    0.78
     elements
    0.77
     facilities
    0.76
     services
    0.76
    Activations Density 0.627%

    No Known Activations