© 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. 4386
    Prev
    Next
    INDEX
    Explanations

    references to technical terms related to technology and software

    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
    597
    +0.17
    0.7%
    1034
    +0.14
    0.6%
    1323
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.17
    0.02
    1323
    +0.14
    0.02
    1778
    +0.14
    0.02
    Negative Logits
     disreg
    -0.93
     cytoplas
    -0.91
     medusa
    -0.76
     maneu
    -0.76
     unce
    -0.75
     unve
    -0.75
     cushi
    -0.74
     impra
    -0.74
     coar
    -0.71
     intermitt
    -0.70
    POSITIVE LOGITS
     terminal
    1.45
    terminal
    1.41
     Terminal
    1.40
    Terminal
    1.36
     terminals
    1.22
     Terminals
    1.10
     TERMIN
    1.00
    TERMIN
    0.97
    termin
    0.92
     termin
    0.90
    Activations Density 0.084%

    No Known Activations