© 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. 1910
    Prev
    Next
    INDEX
    Explanations

    mentions of non-profit organizations

    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
    1233
    +0.09
    0.3%
    37
    +0.07
    0.2%
    1757
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.09
    0.04
    1556
    +0.07
    0.03
    1737
    +0.07
    0.03
    Negative Logits
     decide
    -0.68
    echo
    -0.63
     colspan
    -0.63
    落
    -0.63
     be
    -0.62
     give
    -0.62
     add
    -0.62
    consulté
    -0.61
     expect
    -0.60
     immediately
    -0.59
    POSITIVE LOGITS
     Juf
    1.88
     disagre
    1.74
     maneu
    1.74
     fta
    1.72
     increa
    1.71
     fuf
    1.65
     ftu
    1.65
     squa
    1.64
     affor
    1.64
     accla
    1.63
    Activations Density 0.305%

    No Known Activations