© 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. 4772
    Prev
    Next
    INDEX
    Explanations

    information related to political parties and legislative activities

    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
    604
    +0.13
    0.4%
    764
    +0.12
    0.3%
    599
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.13
    0.06
    81
    +0.12
    0.03
    239
    +0.09
    0.05
    Negative Logits
    <bos>
    -0.86
    GEBURTSDATUM
    -0.52
    datable
    -0.51
     gls
    -0.50
     začet
    -0.48
    CUSS
    -0.46
     ILLUSTRATIONS
    -0.46
     télécharge
    -0.45
    haviour
    -0.43
    timacy
    -0.43
    POSITIVE LOGITS
     Somal
    0.58
     Crédit
    0.58
     Demokrat
    0.57
    Historio
    0.56
     Godt
    0.56
     Guel
    0.56
     Riks
    0.55
     Biar
    0.55
     Kome
    0.53
     Hiros
    0.53
    Activations Density 0.606%

    No Known Activations