© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 7073
    Prev
    Next
    INDEX
    Explanations

    information related to various 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.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
    50
    +0.22
    1.4%
    1296
    +0.10
    0.7%
    812
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1296
    +0.22
    0.06
    812
    +0.10
    0.06
    597
    +0.09
    0.06
    Negative Logits
    <bos>
    -3.34
    /***
    -0.77
     rehabilitate
    -0.71
     relocate
    -0.71
     assimilate
    -0.70
     familiarize
    -0.69
    /*++
    -0.69
     reinstate
    -0.66
     inaugurate
    -0.65
     neutralize
    -0.65
    POSITIVE LOGITS
     unlaw
    1.25
     véhic
    1.22
     ecru
    1.21
     soulign
    1.18
     maroc
    1.17
     Juf
    1.17
     swarovski
    1.14
     affor
    1.13
     déliv
    1.13
     pleins
    1.13
    Activations Density 0.142%

    No Known Activations