© 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. 6307
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific entity named "Columbia" such as places, organizations, and individuals

    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
    874
    +0.18
    0.8%
    1035
    +0.16
    0.7%
    1741
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.18
    0.04
    1035
    +0.16
    0.03
    874
    +0.13
    0.03
    Negative Logits
    Datuak
    -0.56
     estekak
    -0.51
     mahd
    -0.49
     sfr
    -0.49
    Při
    -0.49
    徨
    -0.48
    htbp
    -0.48
    BaseAdapter
    -0.46
    elemField
    -0.46
    Sinopse
    -0.45
    POSITIVE LOGITS
     Columbia
    1.34
    Columbia
    1.24
     COLUMBIA
    1.21
     columbia
    1.07
    columbia
    0.97
     Columb
    0.92
     Colombia
    0.86
     Thompson
    0.83
    UMBIA
    0.82
     Colomb
    0.79
    Activations Density 0.192%

    No Known Activations