© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5795
    Prev
    Next
    INDEX
    Explanations

    names of celebrities or prominent personalities named Jerry

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    555
    +0.16
    0.9%
    966
    +0.15
    0.8%
    1437
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.16
    0.04
    555
    +0.15
    0.03
    783
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.53
    Vegeu
    -0.67
    lccccc
    -0.61
     Normdatei
    -0.58
    cli
    -0.57
    sim
    -0.55
     linkovi
    -0.54
    nacional
    -0.53
    segundo
    -0.53
    klaim
    -0.52
    POSITIVE LOGITS
     Jerry
    1.57
     jerry
    1.57
    Jerry
    1.52
    jerry
    1.38
     Minang
    1.30
     sml
    1.10
     Muhamma
    1.04
     garcia
    1.01
     jawa
    1.01
     Putih
    1.00
    Activations Density 0.394%

    No Known Activations