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. 6186
    Prev
    Next
    INDEX
    Explanations

    information related to technology companies

    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%
    678
    +0.11
    0.4%
    198
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.24
    -0.05
    717
    +0.11
    0.06
    227
    +0.08
    0.11
    Negative Logits
    <bos>
    -2.69
    ⓧ
    -0.89
    <?
    -0.72
    /**
    -0.71
    /***
    
    -0.70
    
    
    -0.68
     arrange
    -0.62
     evacuate
    -0.62
     reunite
    -0.62
     inaugurate
    -0.59
    POSITIVE LOGITS
     riva
    1.21
     paradiso
    1.09
     soggior
    1.07
     Pekan
    1.07
     Karang
    1.06
     Minang
    1.05
     jawa
    1.04
     riviera
    1.02
     eiffel
    1.01
     ducati
    1.01
    Activations Density 2.696%

    No Known Activations