© 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. 11270
    Prev
    Next
    INDEX
    Explanations

    opinions or statements related to politics or international relations

    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
    872
    +0.10
    0.3%
    1150
    +0.10
    0.3%
    1291
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1291
    +0.10
    0.10
    16
    +0.10
    0.09
    468
    +0.09
    0.06
    Negative Logits
     répondit
    -0.66
     paisley
    -0.54
    iddhar
    -0.53
     albero
    -0.53
     specchio
    -0.52
     getHeight
    -0.51
     indestru
    -0.50
     sculptured
    -0.50
     ritratto
    -0.49
     Whence
    -0.49
    POSITIVE LOGITS
     statement
    0.88
     phrase
    0.83
     frase
    0.81
     sentence
    0.78
     words
    0.78
     statements
    0.76
     wording
    0.75
    statement
    0.72
     ideolog
    0.68
     quote
    0.67
    Activations Density 1.040%

    No Known Activations