© 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. 4492
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of electronic devices

    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
    1385
    +0.14
    0.4%
    964
    +0.12
    0.4%
    872
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.14
    0.07
    1200
    +0.12
    0.05
    1935
    +0.11
    0.04
    Negative Logits
     dises
    -1.17
     hcm
    -1.09
     Ibidem
    -1.08
     Cfr
    -1.07
     akut
    -1.07
     Juf
    -1.06
     simplif
    -1.06
     endom
    -1.04
     panik
    -1.02
     Banten
    -1.01
    POSITIVE LOGITS
     aesthetic
    0.74
     aesthetically
    0.71
     look
    0.70
     aesthetics
    0.68
     looks
    0.67
     visually
    0.66
     design
    0.64
    look
    0.62
    aesthetic
    0.59
    design
    0.58
    Activations Density 0.624%

    No Known Activations