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. 6734
    Prev
    Next
    INDEX
    Explanations

    locations and businesses information, such as dealerships and stores, and details like addresses and services provided

    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
    +0.13
    0.5%
    615
    +0.07
    0.2%
    908
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.13
    0.08
    189
    +0.07
    0.07
    227
    +0.06
    0.08
    Negative Logits
    <bos>
    -1.98
     endow
    -0.88
    ///**
    -0.88
     intersper
    -0.82
    
    
    -0.78
    <?
    -0.78
     quitted
    -0.74
    <?
    
    -0.73
     disambigu
    -0.72
     disbur
    -0.72
    POSITIVE LOGITS
     véhic
    0.82
     soulign
    0.79
     tantôt
    0.76
     prét
    0.75
     prétend
    0.72
     déliv
    0.72
    widetext
    0.71
     marea
    0.70
     délib
    0.69
     aveug
    0.68
    Activations Density 0.876%

    No Known Activations