© 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. 12716
    Prev
    Next
    INDEX
    Explanations

    legal and government-related job titles and roles

    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
    316
    +0.12
    0.4%
    1870
    +0.10
    0.3%
    1177
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.12
    0.03
    1041
    +0.10
    0.02
    316
    +0.09
    0.03
    Negative Logits
    bardziej
    -0.50
     overcoat
    -0.50
     carbonates
    -0.49
     useCallback
    -0.49
     getSize
    -0.49
     créateur
    -0.47
    getreten
    -0.47
     indigestion
    -0.47
     skimage
    -0.46
     smtplib
    -0.45
    POSITIVE LOGITS
     alkoh
    0.85
     kollek
    0.80
     Mémoires
    0.77
     deputy
    0.76
     Bâ
    0.74
     assistant
    0.74
     fré
    0.73
    assistant
    0.73
     akut
    0.72
     Keny
    0.72
    Activations Density 0.084%

    No Known Activations