© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1234
    Prev
    Next
    INDEX
    Explanations

    references to sports teams or sports-related activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1456
    +0.08
    0.2%
    1136
    +0.07
    0.2%
    632
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1884
    +0.08
    0.03
    12
    +0.07
    0.04
    565
    +0.07
    0.04
    Negative Logits
     kosme
    -0.58
     akus
    -0.55
    ();)
    -0.55
     alkoh
    -0.54
     solidar
    -0.54
     kapital
    -0.53
     konsult
    -0.53
     praktik
    -0.52
     invester
    -0.50
     krim
    -0.50
    POSITIVE LOGITS
     germain
    1.02
     medesimo
    0.98
     tramonto
    0.96
     paradiso
    0.93
     cammino
    0.87
     wattpad
    0.85
     genshin
    0.85
     paesaggio
    0.85
     particolar
    0.85
     traffico
    0.84
    Activations Density 0.375%

    No Known Activations