© 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. 13378
    Prev
    Next
    INDEX
    Explanations

    phrases related to learning techniques or exercises

    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
    1978
    +0.10
    0.3%
    1577
    +0.08
    0.2%
    876
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.10
    0.08
    83
    +0.08
    0.04
    1415
    +0.07
    0.02
    Negative Logits
     dises
    -1.10
     Keny
    -1.08
     dispen
    -1.03
     Augu
    -0.99
     Khart
    -0.95
     Juf
    -0.94
     ausp
    -0.94
     sii
    -0.89
     Rumania
    -0.89
     seiz
    -0.89
    POSITIVE LOGITS
     mastered
    0.83
     mastering
    0.79
     skill
    0.77
     mastery
    0.75
     practice
    0.73
     beginner
    0.71
     proficiency
    0.69
     practicing
    0.68
     practiced
    0.68
     skills
    0.68
    Activations Density 0.811%

    No Known Activations