© 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. 5726
    Prev
    Next
    INDEX
    Explanations

    number-related phrases (e.g., numerical counts, specific quantities, and numerical descriptors)

    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
    198
    +0.17
    0.5%
    776
    +0.15
    0.5%
    478
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.17
    0.07
    198
    +0.15
    0.06
    609
    +0.11
    0.05
    Negative Logits
     accla
    -0.80
     Fasc
    -0.72
     tph
    -0.70
     Arro
    -0.69
     Aprile
    -0.69
     Realt
    -0.68
     parteci
    -0.68
     ausp
    -0.68
     Certo
    -0.68
    :,,
    -0.66
    POSITIVE LOGITS
    dozen
    0.64
     dozen
    0.63
     thousand
    0.53
    %
    0.52
    0
    0.52
    thousand
    0.52
     hundred
    0.49
    hundred
    0.48
     different
    0.48
    bondale
    0.47
    Activations Density 0.194%

    No Known Activations