© 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. 6549
    Prev
    Next
    INDEX
    Explanations

    data structures and syntax used in programming

    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
    553
    +0.15
    0.6%
    662
    +0.14
    0.5%
    200
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.15
    0.02
    553
    +0.14
    0.02
    489
    +0.14
    0.01
    Negative Logits
    </h2>
    -0.49
     Clark
    -0.48
     Charles
    -0.47
     Chin
    -0.46
    ('.');
    -0.46
     UT
    -0.46
    PerformLayout
    -0.45
    </h1>
    -0.45
     Ul
    -0.45
     Chi
    -0.44
    POSITIVE LOGITS
     bandung
    0.89
     kebaya
    0.89
     tanong
    0.86
     jati
    0.83
     mosso
    0.83
     bahay
    0.80
     soste
    0.80
     Ottobre
    0.80
     surabaya
    0.79
     jaya
    0.78
    Activations Density 0.089%

    No Known Activations