© 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. 5522
    Prev
    Next
    INDEX
    Explanations

    references to physical positions or physical actions such as standing

    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
    397
    +0.12
    0.4%
    1516
    +0.12
    0.4%
    1370
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1370
    +0.12
    0.05
    397
    +0.12
    0.04
    1516
    +0.11
    0.04
    Negative Logits
    ņi
    -0.54
    ņas
    -0.51
     Dele
    -0.46
     Pursu
    -0.46
    ļi
    -0.45
    numerusform
    -0.44
     Partly
    -0.44
     Projek
    -0.43
     De
    -0.42
     kabel
    -0.42
    POSITIVE LOGITS
     STAND
    1.14
     stand
    1.09
     stands
    1.04
     standing
    0.99
     stood
    0.98
    stand
    0.97
    Stand
    0.96
     Stands
    0.95
    Standing
    0.93
     Stand
    0.92
    Activations Density 0.117%

    No Known Activations