© 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. 1071
    Prev
    Next
    INDEX
    Explanations

    references to digital devices and features such as iCloud, Safari tabs, and app protection for Apple devices

    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
    1146
    +0.08
    0.2%
    283
    +0.07
    0.2%
    1089
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.04
    1343
    +0.07
    0.06
    1927
    +0.06
    0.06
    Negative Logits
     don
    -1.03
     so
    -1.03
     me
    -1.03
     re
    -1.01
     far
    -0.98
    ,
    -0.97
     res
    -0.96
     just
    -0.96
     do
    -0.96
     get
    -0.95
    POSITIVE LOGITS
     fta
    2.97
     ?...
    2.95
     thut
    2.91
     ftu
    2.90
     !...
    2.89
     increa
    2.88
     effe
    2.84
     squa
    2.83
     fei
    2.82
     maneu
    2.81
    Activations Density 0.323%

    No Known Activations