© 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. 845
    Prev
    Next
    INDEX
    Explanations

    Java programming-related terms and concepts

    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
    690
    +0.11
    0.4%
    1871
    +0.10
    0.4%
    1265
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.11
    0.11
    1120
    +0.10
    0.10
    1080
    +0.10
    0.08
    Negative Logits
     continue
    -0.99
     put
    -0.99
     do
    -0.99
     pass
    -0.99
     dis
    -0.98
     so
    -0.98
     enable
    -0.95
     go
    -0.95
     make
    -0.95
     find
    -0.95
    POSITIVE LOGITS
     stockholm
    2.76
     Juf
    2.67
     effe
    2.62
     fta
    2.60
     wien
    2.58
     increa
    2.57
     madonna
    2.57
     eiffel
    2.56
     maneu
    2.54
     accla
    2.52
    Activations Density 0.730%

    No Known Activations