© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5740
    Prev
    Next
    INDEX
    Explanations

    locations, such as countries and cities

    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
    50
    +0.21
    0.8%
    990
    +0.07
    0.3%
    1983
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1252
    +0.21
    0.10
    227
    +0.07
    0.10
    1479
    +0.07
    0.08
    Negative Logits
    <bos>
    -2.57
    ⓧ
    -0.87
     serve
    -0.69
    
    -0.66
    /***
    -0.63
    lateinit
    -0.61
    /**
    -0.61
    ždý
    -0.60
    Kontrola
    -0.59
     apply
    -0.59
    POSITIVE LOGITS
     Juf
    1.69
     bordeaux
    1.63
     maneu
    1.51
     Cæ
    1.50
     carrefour
    1.48
     marseille
    1.48
     emphat
    1.47
     Præ
    1.47
     wien
    1.47
     eiffel
    1.44
    Activations Density 1.253%

    No Known Activations