© 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. 7169
    Prev
    Next
    INDEX
    Explanations

    regional references and descriptions

    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
    +0.20
    0.7%
    314
    +0.16
    0.5%
    678
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.20
    0.04
    678
    +0.16
    0.04
    1705
    +0.15
    0.04
    Negative Logits
    AutoScaleMode
    -0.63
    JoinTable
    -0.61
    BaseAdapter
    -0.59
    IsRequired
    -0.56
    IsUnicode
    -0.56
    AlterField
    -0.55
    CreateIndex
    -0.52
    NullException
    -0.51
    InnerText
    -0.50
    AddField
    -0.49
    POSITIVE LOGITS
     meis
    1.00
     paff
    1.00
     pietre
    0.99
     aen
    0.98
     nomine
    0.95
     ivi
    0.93
     fep
    0.93
     ftu
    0.91
     Augu
    0.90
     fatis
    0.90
    Activations Density 0.205%

    No Known Activations