© 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. 2382
    Prev
    Next
    INDEX
    Explanations

    ratings on products or services

    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
    1562
    +0.06
    0.2%
    1618
    +0.06
    0.2%
    50
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1118
    +0.06
    0.03
    1738
    +0.06
    0.02
    732
    +0.06
    0.02
    Negative Logits
    ैसे
    -0.64
    결
    -0.63
     serve
    -0.61
     manage
    -0.60
     continue
    -0.59
    습니다
    -0.59
    يا
    -0.59
    ,
    -0.59
     front
    -0.59
    ItemBackground
    -0.58
    POSITIVE LOGITS
    Rated
    2.35
     Rated
    2.23
     impra
    1.92
     maneu
    1.92
     affor
    1.89
     hairc
    1.84
     rated
    1.81
     ecru
    1.79
     excru
    1.78
     swarovski
    1.72
    Activations Density 0.182%

    No Known Activations