© 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. 0-RES-JB
    11. 275
    Prev
    Next
    INDEX
    Explanations

    important entities or locations

    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
    331
    +0.07
    0.2%
    665
    +0.07
    0.2%
    805
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.02
    1343
    +0.07
    0.03
    762
    +0.06
    0.02
    Negative Logits
    ਼
    -0.69
     września
    -0.66
     respond
    -0.64
     springfox
    -0.64
     enter
    -0.64
     due
    -0.63
     consider
    -0.62
     avoid
    -0.62
     gain
    -0.62
     cả
    -0.62
    POSITIVE LOGITS
    ico
    2.20
     squa
    2.09
     increa
    2.06
     suscep
    2.03
     affor
    1.99
     erad
    1.95
     inev
    1.88
     maneu
    1.88
     volunte
    1.87
     impra
    1.87
    Activations Density 0.203%

    No Known Activations