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. 0-RES-JB
    6. 30
    Prev
    Next
    INDEX
    Explanations

    information regarding copyright ownership and permissions

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1150
    +0.10
    0.4%
    50
    +0.07
    0.3%
    789
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1109
    +0.10
    0.04
    1802
    +0.07
    0.04
    1150
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.44
    /**
    -0.72
    <!--
    
    -0.71
    /*
    -0.71
     pull
    -0.70
    ുറ
    -0.68
    ⓧ
    -0.67
     run
    -0.65
    解
    -0.64
     expand
    -0.63
    POSITIVE LOGITS
     copyrighted
    2.07
     maneu
    1.72
     affor
    1.71
     Juf
    1.63
     impra
    1.63
     maroc
    1.62
     philanth
    1.61
     eiffel
    1.61
     suscep
    1.59
     swarovski
    1.58
    Activations Density 0.104%

    No Known Activations