© 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 EvalsExportsinterp-engineNEWAPI 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. 5240
    Prev
    Next
    INDEX
    Explanations

    information related to scientific studies and research processes

    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
    1479
    +0.07
    0.2%
    1001
    +0.07
    0.2%
    478
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.07
    0.06
    586
    +0.07
    0.05
    1001
    +0.07
    0.05
    Negative Logits
     tanga
    -1.01
     hcm
    -1.00
     mef
    -1.00
     canel
    -0.99
     levis
    -0.97
     centrif
    -0.97
     tuta
    -0.94
     baf
    -0.91
     saba
    -0.91
     olx
    -0.90
    POSITIVE LOGITS
     nonetheless
    1.26
     nevertheless
    1.24
     comunque
    0.74
     зато
    0.69
     digress
    0.66
     ändå
    0.65
    Nevertheless
    0.61
    Nonetheless
    0.59
     toch
    0.59
     still
    0.59
    Activations Density 0.448%

    No Known Activations