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. 5703
    Prev
    Next
    INDEX
    Explanations

    technical specifications and product names related to electronic devices

    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
    +0.24
    0.9%
    227
    +0.12
    0.5%
    1978
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.24
    0.04
    1978
    +0.12
    0.11
    227
    +0.11
    0.11
    Negative Logits
    <bos>
    -3.46
    ⓧ
    -1.10
    
    
    -0.96
    <?
    -0.88
    },[])
    -0.85
    /**
    -0.81
    <?
    
    -0.78
    contentLoaded
    -0.72
    ///**
    -0.70
     дописавши
    -0.70
    POSITIVE LOGITS
     effray
    0.78
     surpren
    0.78
     curieux
    0.76
     vasi
    0.72
     élégant
    0.71
     éton
    0.71
     habile
    0.69
     malheureux
    0.69
     beverly
    0.68
     délib
    0.66
    Activations Density 0.950%

    No Known Activations