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

    Neuronpedia

    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. 13472
    Prev
    Next
    INDEX
    Explanations

    highly regulated or restricted conditions related to rules or prohibitions

    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
    1145
    +0.12
    0.4%
    1896
    +0.11
    0.4%
    889
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.12
    0.03
    1056
    +0.11
    0.03
    147
    +0.10
    0.02
    Negative Logits
     maneu
    -0.81
     attemp
    -0.73
     shenan
    -0.66
     encomp
    -0.65
     impra
    -0.65
     reconno
    -0.65
     resear
    -0.64
     reluct
    -0.64
     abbandon
    -0.62
     suscep
    -0.61
    POSITIVE LOGITS
     strict
    0.73
     Exacts
    0.66
    SEVERE
    0.66
     hornblende
    0.65
     severe
    0.64
    strict
    0.64
    postolic
    0.64
    Strict
    0.63
     harsh
    0.62
    severe
    0.61
    Activations Density 0.104%

    No Known Activations