© 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. 13459
    Prev
    Next
    INDEX
    Explanations

    technical terms related to heat sources, power generation equipment, and circuit components

    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
    1385
    +0.17
    0.5%
    1438
    +0.16
    0.5%
    1870
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.17
    0.07
    513
    +0.16
    0.05
    2044
    +0.13
    0.06
    Negative Logits
     depic
    -1.25
     fortn
    -1.21
     seiz
    -1.20
     increa
    -1.19
     eyel
    -1.16
     dises
    -1.15
     aen
    -1.15
     erad
    -1.14
     Minang
    -1.13
     emphat
    -1.13
    POSITIVE LOGITS
     itself
    0.83
    '
    0.72
    ’
    0.68
     during
    0.60
    .
    0.56
    body
    0.54
    ATEGY
    0.53
    `
    0.53
     while
    0.53
     via
    0.53
    Activations Density 0.389%

    No Known Activations