© 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. 14676
    Prev
    Next
    INDEX
    Explanations

    ^words related to financial or political controversy

    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
    990
    +0.12
    0.4%
    347
    +0.11
    0.3%
    1820
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.12
    0.07
    347
    +0.11
    0.05
    1820
    +0.09
    0.05
    Negative Logits
     vogliamo
    -0.66
     trovo
    -0.62
     abbiano
    -0.62
    picuous
    -0.61
     BIBSYS
    -0.60
     dovre
    -0.58
     avrebbero
    -0.56
     facciamo
    -0.56
     succede
    -0.56
     vogli
    -0.55
    POSITIVE LOGITS
     unce
    0.72
     trefoil
    0.62
     of
    0.60
     squa
    0.59
     unden
    0.58
     frow
    0.58
     macrop
    0.56
     pite
    0.56
     friable
    0.56
     tolerably
    0.55
    Activations Density 0.369%

    No Known Activations