© 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. 6320
    Prev
    Next
    INDEX
    Explanations

    information related to various sports teams and events

    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
    1994
    +0.18
    1.0%
    228
    +0.15
    0.8%
    874
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1994
    +0.18
    0.04
    1575
    +0.15
    0.04
    1056
    +0.14
    0.04
    Negative Logits
     reluct
    -1.11
     ingrat
    -1.03
     shenan
    -0.99
     vainly
    -0.95
     intersper
    -0.94
     disgra
    -0.91
     felicity
    -0.91
     quitted
    -0.90
     gaily
    -0.89
     disagre
    -0.89
    POSITIVE LOGITS
     Cleveland
    1.42
     Cle
    1.39
    Cleveland
    1.38
     CLE
    1.37
    Cle
    1.32
    CLE
    1.26
    cle
    1.25
     cle
    1.20
    VELAND
    1.06
     Clemson
    0.98
    Activations Density 0.480%

    No Known Activations