Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 242
    Prev
    Next
    INDEX
    Explanations

    terms related to government and political organization, specifically focusing on administrative and legislative processes

    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
    +0.14
    0.6%
    1842
    +0.11
    0.5%
    25
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1325
    +0.14
    0.07
    25
    +0.11
    0.07
    353
    +0.11
    0.06
    Negative Logits
    <bos>
    -2.83
    Vegeu
    -0.94
    PerformLayout
    -0.90
    ValueGenerated
    -0.77
    HasIndex
    -0.71
    Referințe
    -0.70
    SharedDtor
    -0.67
    HasColumnType
    -0.66
    public
    -0.65
    Trọng
    -0.65
    POSITIVE LOGITS
     fta
    1.91
     stockholm
    1.86
     secon
    1.79
     increa
    1.78
     wherea
    1.78
     thut
    1.74
     Augu
    1.70
     effe
    1.70
     inev
    1.68
     fortn
    1.67
    Activations Density 0.886%

    No Known Activations