© 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. 0-RES-JB
    11. 907
    Prev
    Next
    INDEX
    Explanations

    references to specific operating systems

    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
    597
    +0.09
    0.3%
    50
    +0.08
    0.3%
    795
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.09
    0.03
    931
    +0.08
    0.02
    1798
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.20
     graças
    -0.68
    <?
    -0.63
     Ainda
    -0.60
     sobretudo
    -0.59
    сында
    -0.57
     deprive
    -0.55
    obenz
    -0.54
    oglobulin
    -0.53
     Embora
    -0.53
    POSITIVE LOGITS
     OS
    2.39
    OS
    1.62
     Os
    1.46
     os
    1.29
    Os
    1.23
     Mémoires
    1.21
     milano
    1.16
     Chapitre
    1.16
     lidl
    1.15
     rafra
    1.15
    Activations Density 0.095%

    No Known Activations