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. 6189
    Prev
    Next
    INDEX
    Explanations

    requests to listen to a podcast

    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
    +0.27
    1.3%
    1059
    +0.09
    0.4%
    101
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    791
    +0.27
    0.03
    1356
    +0.09
    0.03
    459
    +0.09
    0.03
    Negative Logits
    <bos>
    -3.42
    ⓧ
    -0.94
    <?
    -0.80
    /*
    -0.79
    /**
    -0.74
    Географи
    -0.73
    
    
    -0.73
    <eos>
    -0.70
    util
    -0.67
    AddColumn
    -0.67
    POSITIVE LOGITS
     maneu
    2.21
     increa
    2.19
     affor
    2.14
     reluct
    2.12
     volunte
    2.09
     guarante
    2.08
     impra
    2.06
     erad
    2.04
     accla
    2.04
     inev
    2.04
    Activations Density 0.134%

    No Known Activations