© 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 EvalsExportsinterp-engineNEWAPI 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. 15207
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms in a research context

    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
    872
    +0.19
    0.7%
    599
    +0.16
    0.5%
    50
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1380
    +0.19
    0.04
    872
    +0.16
    0.13
    599
    +0.13
    0.10
    Negative Logits
     gesta
    -0.90
     Transfermarkt
    -0.81
     NKC
    -0.77
     notor
    -0.76
     cera
    -0.76
     interag
    -0.75
     Senat
    -0.74
     atle
    -0.74
     Distrikt
    -0.74
     bronz
    -0.73
    POSITIVE LOGITS
     shenan
    1.13
     disreg
    1.11
     wikihow
    1.09
     milf
    1.08
     lmfao
    1.04
     mcdonald
    1.04
     snoopy
    1.01
     Considerable
    1.01
     embodi
    1.01
     🤣🤣
    1.00
    Activations Density 1.939%

    No Known Activations