© 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. 11580
    Prev
    Next
    INDEX
    Explanations

    names with 'Jr' at the end

    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
    687
    +0.12
    0.4%
    501
    +0.10
    0.3%
    281
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    687
    +0.12
    0.02
    281
    +0.10
    0.02
    1170
    +0.10
    0.02
    Negative Logits
     raste
    -0.61
     šte
    -0.60
    tiqueta
    -0.57
     anta
    -0.53
     inteligen
    -0.52
    película
    -0.51
     gres
    -0.49
    Ży
    -0.49
     takk
    -0.49
     opar
    -0.48
    POSITIVE LOGITS
     Jr
    0.94
     Middles
    0.89
     impra
    0.87
     Mlle
    0.86
     unspeak
    0.85
     jr
    0.84
     accla
    0.79
    Jr
    0.79
     disgra
    0.79
     philanth
    0.79
    Activations Density 0.040%

    No Known Activations