© 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. 4800
    Prev
    Next
    INDEX
    Explanations

    names of football clubs

    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
    889
    +0.25
    1.1%
    479
    +0.18
    0.8%
    421
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    889
    +0.25
    0.03
    421
    +0.18
    0.03
    479
    +0.17
    0.03
    Negative Logits
    rungsseite
    -0.72
    asserole
    -0.61
    OGND
    -0.59
     affatto
    -0.56
     dicendo
    -0.56
    municipi
    -0.54
    mistak
    -0.54
     perciò
    -0.53
     giusti
    -0.51
     gius
    -0.50
    POSITIVE LOGITS
     Chelsea
    1.47
    Chelsea
    1.36
     chelsea
    1.03
    chelsea
    1.00
     Blues
    0.82
     Chel
    0.72
     Stamford
    0.70
     blues
    0.67
    Blues
    0.67
     Ches
    0.66
    Activations Density 0.136%

    No Known Activations