© 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. 133
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities, possibly related to criminal activities or locations

    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
    404
    +0.10
    0.3%
    172
    +0.09
    0.3%
    90
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.04
    1343
    +0.09
    0.04
    1194
    +0.09
    0.03
    Negative Logits
     Mère
    -1.32
     Meilleur
    -1.04
     Aéroport
    -0.98
     paillettes
    -0.98
     Comédie
    -0.95
     Sén
    -0.91
     Messieurs
    -0.88
     Septembre
    -0.87
     Famille
    -0.85
     chèvre
    -0.85
    POSITIVE LOGITS
     Cou
    2.23
     Bou
    1.92
     cou
    1.88
    Cou
    1.86
    Bou
    1.73
    cou
    1.72
     Sou
    1.70
     Kou
    1.70
    Kou
    1.64
     Mou
    1.62
    Activations Density 0.243%

    No Known Activations