© 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. 5809
    Prev
    Next
    INDEX
    Explanations

    statements discussing legal regulations and intricacies

    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
    184
    +0.15
    0.4%
    872
    +0.13
    0.4%
    394
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.15
    0.02
    1572
    +0.13
    0.04
    198
    +0.11
    0.04
    Negative Logits
     pessi
    -1.05
     Immig
    -0.98
     reluct
    -0.97
     inev
    -0.96
     wherea
    -0.95
     fortn
    -0.93
     Keny
    -0.89
     dilap
    -0.89
     berea
    -0.88
     impra
    -0.88
    POSITIVE LOGITS
     &___
    0.62
     springfox
    0.61
    ofern
    0.56
    indest
    0.54
    RectangleBorder
    0.52
     OrderedDict
    0.51
    ércoles
    0.51
    uluş
    0.50
    ]?.
    0.50
     toiminta
    0.49
    Activations Density 0.523%

    No Known Activations