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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6323
    Prev
    Next
    INDEX
    Explanations

    information related to current status or availability

    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
    +0.21
    1.1%
    1742
    +0.12
    0.6%
    479
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.21
    0.05
    1742
    +0.12
    0.05
    1589
    +0.12
    0.04
    Negative Logits
    <bos>
    -3.05
    ⓧ
    -0.86
    ///**
    -0.66
     mobilize
    -0.66
    /***
    
    -0.65
     deepen
    -0.65
     abolish
    -0.64
     stimulate
    -0.63
     intensify
    -0.62
    //--
    -0.62
    POSITIVE LOGITS
     embodi
    1.48
     squa
    1.42
     maneu
    1.37
     stockholm
    1.36
     Juf
    1.35
     fta
    1.34
     accla
    1.34
     chrysler
    1.33
     ftu
    1.33
     wien
    1.31
    Activations Density 0.149%

    No Known Activations