© 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. 6-RES-JB
    11. 2954
    Prev
    Next
    INDEX
    Explanations

    names

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1023
    +0.18
    1.0%
    390
    +0.15
    0.8%
    1961
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.18
    0.00
    1097
    +0.15
    0.06
    1984
    +0.13
    0.06
    Negative Logits
    <bos>
    -0.75
    awtextra
    -0.68
     onCancelled
    -0.60
     препратки
    -0.57
    CommandText
    -0.56
    čního
    -0.53
     swing
    -0.52
     يتيمه
    -0.52
     ficaram
    -0.52
    lhes
    -0.52
    POSITIVE LOGITS
     laura
    1.15
     LAURA
    1.07
     Laura
    1.02
    Laura
    0.99
    laura
    0.98
    LAURA
    0.91
     Confu
    0.89
     shenan
    0.88
     sovere
    0.87
     tupperware
    0.87
    Activations Density 0.600%

    No Known Activations