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. 7785
    Prev
    Next
    INDEX
    Explanations

    references to global or international contexts

    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
    +0.34
    1.2%
    2034
    +0.20
    0.7%
    227
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2034
    +0.34
    0.06
    1438
    +0.20
    0.05
    227
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.07
    ///**
    -0.76
    /***
    
    -0.74
     maig
    -0.66
    ɵɵelement
    -0.65
    //{
    
    -0.61
     febr
    -0.61
     Marzo
    -0.61
    Molto
    -0.60
     interessa
    -0.59
    POSITIVE LOGITS
     ecru
    0.96
     cuck
    0.93
     Middles
    0.89
     ankara
    0.89
     maneu
    0.89
     outlander
    0.88
     Inhabitants
    0.87
     alps
    0.85
     unwarran
    0.84
    truction
    0.84
    Activations Density 0.258%

    No Known Activations