© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7235
    Prev
    Next
    INDEX
    Explanations

    political entity references, particularly wards and councils

    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
    1896
    +0.15
    0.8%
    406
    +0.13
    0.7%
    1983
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.15
    0.02
    1896
    +0.13
    0.02
    1328
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.36
    columnwidth
    -0.61
    ثيق
    -0.60
    isContained
    -0.60
     šķ
    -0.60
    IVEREF
    -0.59
    explo
    -0.58
    TagHelpers
    -0.56
    archiviato
    -0.55
    prnewswire
    -0.55
    POSITIVE LOGITS
     Ward
    1.73
     WARD
    1.67
    Ward
    1.65
     ward
    1.53
     ricardo
    1.23
     wards
    1.22
     sergio
    1.20
     stockholm
    1.13
    WARD
    1.11
     pylab
    1.10
    Activations Density 0.399%

    No Known Activations