© 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. 6294
    Prev
    Next
    INDEX
    Explanations

    descriptions of minimalistic designs

    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
    1290
    +0.10
    0.3%
    872
    +0.10
    0.3%
    297
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1290
    +0.10
    0.05
    2044
    +0.10
    0.05
    872
    +0.09
    0.05
    Negative Logits
     accla
    -1.14
     §.
    -1.13
     inappro
    -1.12
     maneu
    -1.11
     secon
    -1.11
     fuf
    -1.10
     excru
    -1.10
     emphat
    -1.10
     inev
    -1.10
     Abbé
    -1.09
    POSITIVE LOGITS
     simplicity
    1.07
     simple
    1.02
    Simple
    0.93
    simple
    0.92
     simpler
    0.89
     simplest
    0.84
     Simple
    0.84
     simples
    0.80
     minimal
    0.80
     minimalist
    0.80
    Activations Density 0.442%

    No Known Activations