© 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. 4138
    Prev
    Next
    INDEX
    Explanations

    social media sharing features

    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
    1403
    +0.08
    0.2%
    576
    +0.08
    0.2%
    697
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    576
    +0.08
    0.03
    1785
    +0.08
    0.03
    1355
    +0.07
    0.02
    Negative Logits
     mariscos
    -0.58
     prostitu
    -0.57
     electrica
    -0.56
     alfab
    -0.55
     verdura
    -0.55
    meja
    -0.53
     concentra
    -0.52
    TextFormField
    -0.52
     aspira
    -0.51
     kontra
    -0.51
    POSITIVE LOGITS
     hairc
    0.84
     cushi
    0.82
     scrat
    0.81
     panasonic
    0.81
     toshiba
    0.80
     gild
    0.77
     pikachu
    0.75
     milf
    0.75
     philips
    0.75
     intersper
    0.73
    Activations Density 0.113%

    No Known Activations