© 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. 7154
    Prev
    Next
    INDEX
    Explanations

    capital cities or locations and their associated details

    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
    •Steering
    descriptions of cities

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.26
    1.0%
    227
    +0.08
    0.3%
    964
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.26
    0.08
    227
    +0.08
    0.08
    766
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.60
    }{||
    -0.70
    šech
    -0.66
    private
    -0.63
    public
    -0.61
     AssemblyCompany
    -0.61
     guangdong
    -0.60
    PreInfinity
    -0.59
     ProtoMessage
    -0.59
    ⓧ
    -0.58
    POSITIVE LOGITS
     unwarran
    1.74
     impra
    1.73
     desir
    1.68
     squa
    1.64
     madonna
    1.63
     unden
    1.63
     fta
    1.61
     lamborghini
    1.60
     Juf
    1.59
     increa
    1.59
    Activations Density 0.702%

    No Known Activations