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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15173
    Prev
    Next
    INDEX
    Explanations

    terms related to real estate and local government activities

    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
    +0.26
    1.5%
    1577
    +0.22
    1.3%
    394
    +0.19
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.26
    0.46
    1013
    +0.22
    0.44
    1177
    +0.19
    -0.04
    Negative Logits
    <bos>
    -2.73
    ⓧ
    -1.02
    <?
    -0.92
    /**
    -0.87
    <eos>
    -0.85
    
    
    -0.81
    /*
    -0.78
    Kontrola
    -0.74
    public
    -0.70
     springfox
    -0.68
    POSITIVE LOGITS
     Juf
    2.12
     accla
    1.94
     Intere
    1.90
     Keny
    1.88
     increa
    1.84
     inev
    1.84
     stockholm
    1.83
     hcm
    1.82
     wien
    1.81
     affor
    1.79
    Activations Density 26.547%

    No Known Activations