© 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. 14831
    Prev
    Next
    INDEX
    Explanations

    legal and bureaucratic language related to specific cases or issues

    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
    1565
    +0.17
    0.6%
    645
    +0.13
    0.5%
    1839
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1565
    +0.17
    0.04
    636
    +0.13
    0.03
    645
    +0.13
    0.03
    Negative Logits
     roh
    -0.63
     prouve
    -0.59
     kula
    -0.58
     kef
    -0.58
     kuh
    -0.57
     kona
    -0.57
     uhr
    -0.56
     bali
    -0.56
     kud
    -0.55
     augus
    -0.55
    POSITIVE LOGITS
     matter
    1.28
    matter
    1.28
     Matter
    1.20
    Matter
    1.20
     matters
    1.15
    matters
    1.08
     MATTER
    1.08
     Matters
    1.06
     mattered
    0.97
    Matters
    0.93
    Activations Density 0.064%

    No Known Activations