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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15149
    Prev
    Next
    INDEX
    Explanations

    the interjection "Hmmm" followed by expressions of doubt or curiosity

    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
    0.7%
    381
    +0.13
    0.5%
    490
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.17
    0.04
    1539
    +0.13
    0.03
    943
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.19
    /***
    
    -1.05
    <?
    
    -0.73
     assiste
    -0.71
    /*!
    
    -0.68
    /*++
    -0.67
    })();
    
    -0.66
    //});
    -0.66
    //}
    
    -0.65
    //{
    
    -0.65
    POSITIVE LOGITS
     friable
    1.06
     maneu
    0.96
     unce
    0.90
     greyish
    0.85
     Czechos
    0.84
     resear
    0.84
     stockholm
    0.84
     [''
    0.83
     coö
    0.82
     prerog
    0.81
    Activations Density 0.135%

    No Known Activations