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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 184
    Prev
    Next
    INDEX
    Explanations

    references to seating arrangements and configurations

    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
    +0.28
    0.9%
    1385
    +0.17
    0.5%
    1843
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.28
    0.05
    609
    +0.17
    0.03
    1192
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.04
    ⓧ
    -0.75
     stopp
    -0.68
     intersper
    -0.66
     reger
    -0.65
     vold
    -0.62
     resourceCulture
    -0.62
     solidar
    -0.60
     thut
    -0.60
     anse
    -0.60
    POSITIVE LOGITS
     Cáceres
    0.81
     Mérida
    0.76
     Cár
    0.71
     Lázaro
    0.69
     asado
    0.66
     Joaqu
    0.66
     Isidro
    0.63
     Asunción
    0.63
     Cádiz
    0.62
     Cárdenas
    0.62
    Activations Density 0.196%

    No Known Activations