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. 6179
    Prev
    Next
    INDEX
    Explanations

    web links or URLs

    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
    1.4%
    1618
    +0.11
    0.8%
    1961
    +0.11
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.21
    0.05
    122
    +0.11
    0.04
    1618
    +0.11
    0.04
    Negative Logits
    <bos>
    -3.17
    <?
    -1.17
    /***
    
    -1.05
    ⓧ
    -1.05
    
    
    -1.04
    /**
    -0.98
    ///**
    -0.77
     vairāk
    -0.72
     /**
    
    -0.71
    <?
    
    -0.70
    POSITIVE LOGITS
     —
    0.88
    ypal
    0.71
    capulco
    0.70
     alé
    0.69
     cias
    0.67
    atung
    0.64
    —
    0.64
     bandung
    0.63
     maroc
    0.62
     jawa
    0.62
    Activations Density 0.099%

    No Known Activations