© 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. 13558
    Prev
    Next
    INDEX
    Explanations

    references to specific equipment or instruments

    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
    +0.15
    0.5%
    1742
    +0.12
    0.4%
    168
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.15
    0.02
    1705
    +0.12
    0.02
    1742
    +0.11
    0.02
    Negative Logits
     affor
    -1.03
     maneu
    -0.95
     increa
    -0.93
     reconno
    -0.92
     guarante
    -0.91
     volunte
    -0.89
     superintend
    -0.88
     sergio
    -0.87
     intersper
    -0.87
     inev
    -0.87
    POSITIVE LOGITS
     equipment
    1.40
     Equipment
    1.30
    equipment
    1.26
    Equipment
    1.21
     EQUIPMENT
    1.15
    ipment
    1.05
     equipments
    0.99
    EQUIPMENT
    0.86
    equipped
    0.85
     equipped
    0.83
    Activations Density 0.079%

    No Known Activations