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. 12-RES-JB
    6. 7865
    Prev
    Next
    INDEX
    Explanations

    references to population statistics or demographic information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.30
    1.0%
    1385
    +0.10
    0.4%
    198
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.30
    0.05
    1385
    +0.10
    0.05
    595
    +0.09
    0.04
    Negative Logits
    <bos>
    -1.67
     intersper
    -0.66
     harmonize
    -0.60
     localize
    -0.56
     inaugurate
    -0.56
     personalise
    -0.55
     mobilize
    -0.54
     rehabilitate
    -0.54
     lengthen
    -0.51
     personalize
    -0.51
    POSITIVE LOGITS
     population
    0.99
     Bekasi
    0.84
     Population
    0.83
    Population
    0.81
     bandung
    0.80
     Palembang
    0.79
     Banjar
    0.78
     Bárbara
    0.78
     Karang
    0.77
     Jambi
    0.74
    Activations Density 0.454%

    No Known Activations