© 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. 10803
    Prev
    Next
    INDEX
    Explanations

    phrases related to limitations or reaching a maximum capacity

    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
    1501
    +0.08
    0.2%
    1547
    +0.07
    0.2%
    1910
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1519
    +0.08
    0.03
    707
    +0.07
    0.04
    1087
    +0.07
    0.02
    Negative Logits
     effe
    -0.78
     Febru
    -0.76
     Keny
    -0.74
     thut
    -0.73
     embra
    -0.72
     opport
    -0.72
     inder
    -0.71
     Augu
    -0.71
     guarante
    -0.70
     emphat
    -0.70
    POSITIVE LOGITS
     further
    1.19
    further
    0.99
    Further
    0.94
     Further
    0.92
     FURTHER
    0.88
     additional
    0.87
    urther
    0.77
     farther
    0.77
    additional
    0.76
     continue
    0.76
    Activations Density 0.555%

    No Known Activations