© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7624
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and regulations, particularly in the context of the government and industry

    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
    1499
    +0.12
    0.4%
    872
    +0.12
    0.4%
    1648
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.12
    0.07
    1105
    +0.12
    0.04
    1617
    +0.08
    0.04
    Negative Logits
     hairc
    -0.95
     fluo
    -0.93
     hentai
    -0.92
     intersper
    -0.90
     snoopy
    -0.89
     yoda
    -0.88
     pixar
    -0.86
     Mlle
    -0.85
     desir
    -0.84
     peppa
    -0.83
    POSITIVE LOGITS
     legislation
    0.66
     enacted
    0.63
     provisions
    0.62
     laws
    0.58
     amended
    0.55
     Act
    0.54
     amendments
    0.53
    Vidite
    0.53
     regulations
    0.53
     law
    0.51
    Activations Density 0.382%

    No Known Activations