© 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. 12227
    Prev
    Next
    INDEX
    Explanations

    references to being correct or incorrect

    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
    674
    +0.11
    0.3%
    272
    +0.09
    0.2%
    662
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    272
    +0.11
    0.02
    1689
    +0.09
    0.02
    1826
    +0.07
    0.01
    Negative Logits
     karton
    -0.65
     maksi
    -0.63
     loh
    -0.59
     solidar
    -0.58
     teras
    -0.57
     antik
    -0.57
     kado
    -0.54
     BIBSYS
    -0.54
     kram
    -0.54
     uhr
    -0.54
    POSITIVE LOGITS
     correctly
    0.95
     wrong
    0.80
    correctly
    0.79
     correct
    0.77
    wrong
    0.72
     incorrectly
    0.72
     WRONG
    0.70
     Correct
    0.68
     Wrong
    0.68
    Correct
    0.65
    Activations Density 0.154%

    No Known Activations