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. 15082
    Prev
    Next
    INDEX
    Explanations

    information about products including their material composition and where they are made

    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
    +0.22
    1.4%
    1472
    +0.12
    0.7%
    976
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1472
    +0.22
    0.06
    976
    +0.12
    0.06
    667
    +0.12
    0.06
    Negative Logits
    <bos>
    -3.32
    <?
    -0.86
    ⓧ
    -0.72
    
    
    -0.69
    /***
    
    -0.64
    /**
    -0.60
     viewWillAppear
    -0.60
     државе
    -0.59
    <?
    
    -0.58
     esternos
    -0.57
    POSITIVE LOGITS
     stockholm
    1.37
     accla
    1.30
     wien
    1.29
     affor
    1.25
     panama
    1.24
     aen
    1.22
     maneu
    1.22
     emphat
    1.22
     salomon
    1.22
     thut
    1.21
    Activations Density 0.145%

    No Known Activations