© 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. 3872
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by a verb in the command form

    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
    1678
    +0.13
    0.5%
    1142
    +0.12
    0.4%
    1742
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1142
    +0.13
    0.05
    1742
    +0.12
    0.05
    1805
    +0.12
    0.04
    Negative Logits
     krab
    -0.61
     diabe
    -0.50
    RTSN
    -0.48
     psycholog
    -0.47
    werf
    -0.47
     lomb
    -0.47
     zub
    -0.46
    zins
    -0.45
    fras
    -0.45
    mybatisplus
    -0.45
    POSITIVE LOGITS
     hold
    1.43
     held
    1.32
     holding
    1.28
     Hold
    1.27
     holds
    1.26
     HOLD
    1.26
    hold
    1.25
    held
    1.24
    Hold
    1.23
    holding
    1.23
    Activations Density 0.139%

    No Known Activations