© 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. 6605
    Prev
    Next
    INDEX
    Explanations

    names of specific entities such as people, organizations, and products

    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
    1343
    +0.21
    0.7%
    227
    +0.15
    0.5%
    1510
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.21
    0.08
    507
    +0.15
    0.06
    981
    +0.13
    0.07
    Negative Logits
    <bos>
    -1.06
    asteroide
    -0.80
    astéro
    -0.72
     "..\..\..\
    -0.70
    !*\
    -0.68
    Autoritní
    -0.68
     Савезне
    -0.66
    excelente
    -0.64
    település
    -0.63
    EndInit
    -0.62
    POSITIVE LOGITS
     apprehen
    1.08
     impra
    0.97
     unspeak
    0.96
     reluct
    0.95
     disagre
    0.95
     snoopy
    0.91
     shenan
    0.91
     ineffec
    0.91
     excru
    0.90
     depic
    0.90
    Activations Density 0.317%

    No Known Activations