© 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. 14669
    Prev
    Next
    INDEX
    Explanations

    dates and indexed lists

    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
    1051
    +0.11
    0.3%
    227
    +0.09
    0.2%
    1150
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.11
    0.05
    284
    +0.09
    0.06
    1051
    +0.08
    0.04
    Negative Logits
     bandung
    -1.28
     jaya
    -1.18
     mef
    -1.14
     hcm
    -1.14
     ordina
    -1.11
     aen
    -1.10
     kasa
    -1.10
     »>
    -1.09
     istan
    -1.09
     dises
    -1.08
    POSITIVE LOGITS
     via
    0.76
     briefly
    0.66
     while
    0.64
     through
    0.63
     shortly
    0.61
    URLEncoder
    0.61
     earlier
    0.60
     AssemblyCompany
    0.59
     rhestr
    0.57
    msgSender
    0.57
    Activations Density 0.529%

    No Known Activations