© 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. 11003
    Prev
    Next
    INDEX
    Explanations

    terms related to expressing opinions and statements by or about individuals

    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
    1965
    +0.08
    0.2%
    507
    +0.07
    0.2%
    651
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.08
    0.05
    598
    +0.07
    0.03
    799
    +0.07
    0.03
    Negative Logits
     Simult
    -0.77
     kask
    -0.72
     Examen
    -0.71
     hcm
    -0.71
     Departement
    -0.70
     zó
    -0.68
     nicolas
    -0.67
     Majest
    -0.66
     franz
    -0.66
     gmbh
    -0.66
    POSITIVE LOGITS
    Może
    0.83
    Natürlich
    0.82
    Vielleicht
    0.74
     technically
    0.73
    Dziękuję
    0.72
    Bardzo
    0.71
    Proč
    0.66
    Dzięki
    0.65
    Przyp
    0.64
    algunos
    0.63
    Activations Density 0.429%

    No Known Activations