© 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. 7134
    Prev
    Next
    INDEX
    Explanations

    proper nouns and adjectives related to business and professionalism

    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
    554
    +0.18
    0.9%
    1961
    +0.13
    0.7%
    528
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.18
    0.03
    757
    +0.13
    0.04
    1343
    +0.13
    0.06
    Negative Logits
    Pao
    -0.65
    حياته
    -0.63
    <bos>
    -0.63
     Porter
    -0.58
     Kni
    -0.57
     Lap
    -0.55
     Asher
    -0.55
    richTextPanel
    -0.55
    حياتها
    -0.55
    Portale
    -0.54
    POSITIVE LOGITS
     murano
    0.94
     swarovski
    0.81
     keen
    0.81
     mitsubishi
    0.75
     Guayaquil
    0.74
     thermomix
    0.74
     zucca
    0.73
     moods
    0.73
     vectra
    0.73
     Recife
    0.73
    Activations Density 0.562%

    No Known Activations