© 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. 2114
    Prev
    Next
    INDEX
    Explanations

    mentions related to educational institutions or awards

    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
    90
    +0.19
    0.8%
    1034
    +0.16
    0.7%
    757
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.19
    0.02
    1034
    +0.16
    0.02
    757
    +0.14
    0.02
    Negative Logits
     disagre
    -0.83
     inext
    -0.81
     encomp
    -0.80
     fath
    -0.80
     indestru
    -0.80
     ecru
    -0.79
     unlaw
    -0.75
     hairc
    -0.75
     unden
    -0.75
     fuf
    -0.74
    POSITIVE LOGITS
     Academy
    1.52
    Academy
    1.46
     academy
    1.43
    academy
    1.19
     academies
    1.12
     ACADEMY
    1.11
     Academies
    1.08
     Acad
    0.95
    Oscar
    0.87
     Oscar
    0.87
    Activations Density 0.093%

    No Known Activations