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. 6-RES-JB
    6. 55
    Prev
    Next
    INDEX
    Explanations

    family relationships and details about individuals, such as names, occupations, and locations

    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
    +0.19
    0.6%
    2044
    +0.09
    0.3%
    1213
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.19
    0.04
    1158
    +0.09
    0.03
    1466
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.49
     intersper
    -1.32
     underval
    -0.92
     overcrow
    -0.89
     quitted
    -0.89
     endow
    -0.89
     disbur
    -0.88
     gratify
    -0.81
     reordered
    -0.79
     repress
    -0.77
    POSITIVE LOGITS
     Şi
    0.81
    Sklici
    0.79
    Život
    0.73
     Vainqueur
    0.72
     toiture
    0.70
    ngdoc
    0.69
     TextFormField
    0.68
     marquées
    0.68
     originaux
    0.68
     habituellement
    0.68
    Activations Density 0.088%

    No Known Activations