© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13215
    Prev
    Next
    INDEX
    Explanations

    references to legal and criminal codes

    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
    1499
    +0.12
    0.4%
    872
    +0.12
    0.3%
    1343
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.12
    0.04
    1597
    +0.12
    0.02
    811
    +0.11
    0.03
    Negative Logits
    stdarg
    -0.67
     paisley
    -0.63
     indescri
    -0.60
    Zunanje
    -0.60
     hairc
    -0.60
     exasper
    -0.58
     cushi
    -0.57
     sophistic
    -0.57
    Genau
    -0.57
     reluct
    -0.56
    POSITIVE LOGITS
     teras
    0.89
     marte
    0.87
     sement
    0.83
     kasa
    0.81
     kafe
    0.81
     torba
    0.81
     silikon
    0.80
     karton
    0.79
     seksi
    0.77
     potest
    0.76
    Activations Density 0.137%

    No Known Activations