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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6098
    Prev
    Next
    INDEX
    Explanations

    requests or mentions made in a discreet or stealthy manner

    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
    +0.16
    0.6%
    1437
    +0.10
    0.4%
    1443
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1443
    +0.16
    0.04
    946
    +0.10
    0.05
    1930
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.27
    /*!
    
    -0.67
    /***
    
    -0.65
    /*++
    -0.61
    //{
    
    -0.57
    ***************/
    -0.56
    displayquote
    -0.55
    //*/
    -0.53
    /**
    
    -0.53
    ఐ
    -0.53
    POSITIVE LOGITS
     frankfurt
    1.02
     stockholm
    1.01
     squa
    1.00
     ricardo
    0.99
     stefan
    0.98
     Minang
    0.98
     seoul
    0.96
    arture
    0.95
     tramont
    0.95
     jorge
    0.94
    Activations Density 0.545%

    No Known Activations