© 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. 795
    Prev
    Next
    INDEX
    Explanations

    references to legal documents and company reports

    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
    1042
    +0.10
    0.3%
    690
    +0.09
    0.2%
    1120
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.10
    0.07
    1445
    +0.09
    0.06
    1859
    +0.08
    0.03
    Negative Logits
     pymysql
    -0.56
    ==""){
    -0.53
     shivered
    -0.52
    =="")
    -0.52
     =="
    -0.50
    ==="
    -0.49
     caufe
    -0.48
    ==='
    -0.48
     beft
    -0.48
     sobbed
    -0.46
    POSITIVE LOGITS
     xxvi
    0.68
     autunno
    0.67
     xxv
    0.63
     xxii
    0.62
     vestito
    0.60
     xxiii
    0.59
     fermo
    0.58
     Routed
    0.57
     CiNii
    0.57
     Amplitude
    0.56
    Activations Density 0.611%

    No Known Activations