© 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. 1279
    Prev
    Next
    INDEX
    Explanations

    information related to events or announcements within a community, including details about individuals, their careers, and educational backgrounds

    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
    555
    +0.13
    0.4%
    662
    +0.11
    0.4%
    1926
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.13
    0.03
    1340
    +0.11
    0.03
    662
    +0.07
    0.03
    Negative Logits
    Giao
    -0.68
    Điều
    -0.68
    Bộ
    -0.65
    Về
    -0.64
    invokeLater
    -0.63
    Cách
    -0.63
    addGroup
    -0.62
    addGap
    -0.62
    Đối
    -0.61
    Sản
    -0.61
    POSITIVE LOGITS
     Hat
    2.36
    Hat
    2.27
     HAT
    2.01
     affor
    1.81
     stockholm
    1.77
     maneu
    1.72
     scrat
    1.72
    HAT
    1.66
     embodi
    1.66
     effe
    1.66
    Activations Density 0.197%

    No Known Activations