© 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. 1016
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns that seem to lean heavily towards the language of Japanese

    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
    1884
    +0.07
    0.2%
    762
    +0.07
    0.2%
    1064
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.07
    0.11
    283
    +0.07
    0.04
    1891
    +0.07
    0.09
    Negative Logits
    上
    -0.91
     on
    -0.89
     up
    -0.89
    交
    -0.88
     into
    -0.87
     over
    -0.87
     for
    -0.84
     out
    -0.84
     don
    -0.84
     at
    -0.83
    POSITIVE LOGITS
     affor
    2.66
     increa
    2.65
     impra
    2.62
     maneu
    2.58
     accla
    2.56
     depic
    2.48
     indestru
    2.42
     embra
    2.42
     stockholm
    2.41
     suscep
    2.41
    Activations Density 0.951%

    No Known Activations