© 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. 1768
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to thoughts or beliefs

    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
    50
    +0.07
    0.3%
    785
    +0.07
    0.2%
    411
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    842
    +0.07
    0.03
    679
    +0.07
    0.03
    1753
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.24
     pay
    -0.67
     arrange
    -0.62
    </tbody>
    -0.61
    <?
    -0.60
    addComponent
    -0.60
    pay
    -0.60
     collect
    -0.59
    InitStruct
    -0.59
     take
    -0.58
    POSITIVE LOGITS
     eiffel
    1.69
     swarovski
    1.64
     minds
    1.61
     maneu
    1.61
     scrat
    1.58
     napoli
    1.56
     ecru
    1.55
     tupperware
    1.54
     lidl
    1.53
     maroc
    1.52
    Activations Density 0.084%

    No Known Activations