© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12770
    Prev
    Next
    INDEX
    Explanations

    proper nouns and phrases related to political, legal, and social 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
    478
    +0.17
    0.6%
    1937
    +0.15
    0.5%
    658
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.17
    0.10
    1937
    +0.15
    0.09
    478
    +0.14
    0.08
    Negative Logits
     bandung
    -1.14
     jaya
    -1.08
     carrefour
    -1.02
     prétend
    -0.98
     remonte
    -0.96
     viendra
    -0.96
    capulco
    -0.96
     confé
    -0.93
     oliveira
    -0.92
     kafe
    -0.92
    POSITIVE LOGITS
     currently
    0.91
     aware
    0.74
     presently
    0.74
     now
    0.72
     pleased
    0.72
     still
    0.70
     able
    0.70
     proud
    0.69
     unable
    0.69
     hoping
    0.68
    Activations Density 0.403%

    No Known Activations