© 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. 12459
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to legal or financial entities and procedures

    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
    169
    +0.15
    0.6%
    161
    +0.14
    0.6%
    25
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1101
    +0.15
    0.02
    25
    +0.14
    0.03
    1921
    +0.14
    0.02
    Negative Logits
     HUB
    -0.44
     Sidney
    -0.44
     Gelatin
    -0.42
    jTable
    -0.42
    Sidney
    -0.40
     Alden
    -0.39
     commonwealth
    -0.39
     Pid
    -0.39
    pico
    -0.38
     Pearson
    -0.38
    POSITIVE LOGITS
     Dra
    1.28
     dra
    1.22
    Dra
    1.17
    dra
    1.06
     DRA
    0.98
     drains
    0.95
     drain
    0.90
     Drag
    0.89
     draining
    0.87
     Drain
    0.86
    Activations Density 0.099%

    No Known Activations