© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    phrases related to referees in a sports context, particularly from basketball games

    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
    341
    +0.08
    0.2%
    1778
    +0.08
    0.2%
    976
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.03
    1343
    +0.08
    0.06
    1120
    +0.06
    0.05
    Negative Logits
     shenan
    -1.59
     encomp
    -1.59
     maneu
    -1.56
     accla
    -1.53
     snoopy
    -1.48
     depic
    -1.48
     cabrio
    -1.46
     hentai
    -1.44
     increa
    -1.42
     gaily
    -1.42
    POSITIVE LOGITS
    gins
    1.54
     Reynolds
    1.01
    ulam
    0.99
    arn
    0.95
    Reynolds
    0.94
    iano
    0.87
    ARANCE
    0.82
    aren
    0.76
     متعلقه
    0.76
    Brainz
    0.75
    Activations Density 0.349%

    No Known Activations