© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    phrases related to music and performance energy

    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
    1964
    +0.08
    0.2%
    1381
    +0.07
    0.2%
    1742
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.08
    0.03
    151
    +0.07
    0.02
    1056
    +0.07
    0.02
    Negative Logits
    currentColor
    -0.66
    জ
    -0.59
    LOYEES
    -0.59
    SpringRunner
    -0.57
     itong
    -0.57
    HasIndex
    -0.56
    public
    -0.55
     siyang
    -0.55
    utico
    -0.54
    പ്പ
    -0.54
    POSITIVE LOGITS
     slam
    2.69
     slamming
    2.23
     slams
    2.21
     Slam
    2.19
    slam
    2.17
    Slam
    1.88
     slammed
    1.84
     Sla
    1.53
     accla
    1.39
     slapping
    1.29
    Activations Density 0.195%

    No Known Activations