© 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. 14401
    Prev
    Next
    INDEX
    Explanations

    information related to studies and statistics

    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
    +0.12
    0.4%
    1473
    +0.08
    0.2%
    674
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1524
    +0.12
    0.04
    1139
    +0.08
    0.04
    236
    +0.07
    0.04
    Negative Logits
     accla
    -2.06
     embra
    -2.06
     fta
    -1.95
     emphat
    -1.87
     igno
    -1.86
     Juf
    -1.85
     depic
    -1.85
     pessi
    -1.83
     fte
    -1.81
     compen
    -1.81
    POSITIVE LOGITS
     elsewhere
    0.87
     for
    0.86
     when
    0.85
     in
    0.81
     thereafter
    0.80
     during
    0.80
     if
    0.79
     towards
    0.75
     across
    0.74
     from
    0.73
    Activations Density 0.276%

    No Known Activations