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. 9056
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptions or comparisons

    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
    +0.17
    1.0%
    1045
    +0.12
    0.7%
    605
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1045
    +0.17
    0.04
    976
    +0.12
    0.04
    1763
    +0.11
    0.04
    Negative Logits
    <bos>
    -3.19
    ⓧ
    -1.06
    glMatrixMode
    -0.73
    glBegin
    -0.72
    glLoadIdentity
    -0.67
    /*!
    
    -0.66
    Бере
    -0.66
    
    
    -0.66
    contentLoaded
    -0.65
    /***
    
    -0.64
    POSITIVE LOGITS
     maroc
    1.64
     napoli
    1.57
     milano
    1.50
     tramont
    1.43
     bordeaux
    1.42
     ananas
    1.40
     bayern
    1.40
     vinci
    1.37
     churrasco
    1.37
     ecru
    1.35
    Activations Density 0.074%

    No Known Activations