© 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. 3923
    Prev
    Next
    INDEX
    Explanations

    medical terms and legal terms

    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
    537
    +0.14
    0.5%
    897
    +0.12
    0.4%
    1870
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.14
    0.03
    573
    +0.12
    0.03
    9
    +0.12
    0.02
    Negative Logits
     disreg
    -0.86
     maneu
    -0.84
     unspeak
    -0.83
     shenan
    -0.82
     unavoid
    -0.79
     indestru
    -0.79
     accla
    -0.78
     vainly
    -0.78
     impra
    -0.77
     indescri
    -0.76
    POSITIVE LOGITS
     Internal
    0.97
    Internal
    0.95
     internal
    0.94
    internal
    0.89
     INTERNAL
    0.78
    internalType
    0.76
    OGND
    0.75
    INTERNAL
    0.75
     مرئيه
    0.74
    ifrance
    0.69
    Activations Density 0.072%

    No Known Activations