© 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. 6381
    Prev
    Next
    INDEX
    Explanations

    names of people and specific numbers

    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
    776
    +0.14
    0.4%
    198
    +0.12
    0.3%
    1535
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.14
    0.07
    198
    +0.12
    0.06
    1861
    +0.09
    0.05
    Negative Logits
     négociations
    -0.76
     vœux
    -0.75
     récompenses
    -0.68
     réunions
    -0.61
    Etimo
    -0.61
     prochaines
    -0.60
    Demografie
    -0.60
     journées
    -0.59
    Morfologia
    -0.58
     nouveautés
    -0.58
    POSITIVE LOGITS
     étu
    0.89
     Punj
    0.88
     viciss
    0.88
     intersper
    0.87
     remonte
    0.87
     mène
    0.86
     exé
    0.84
     remplace
    0.82
     reconno
    0.78
     contribue
    0.78
    Activations Density 0.342%

    No Known Activations