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. 5320
    Prev
    Next
    INDEX
    Explanations

    location names and cultural references

    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
    1.0%
    1870
    +0.16
    0.9%
    1671
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.17
    0.06
    667
    +0.16
    0.06
    410
    +0.09
    0.06
    Negative Logits
    <bos>
    -3.03
    ⓧ
    -0.96
    
    
    -0.87
    /**
    -0.81
    CreateIndex
    -0.78
    apnews
    -0.76
    <?
    -0.75
    orElseThrow
    -0.74
     get
    -0.72
    SourceChecksum
    -0.71
    POSITIVE LOGITS
     napoli
    1.80
     Augu
    1.77
     aen
    1.73
     milano
    1.72
     ftu
    1.68
     fatis
    1.65
     verona
    1.63
     fta
    1.63
    fordable
    1.62
     bandung
    1.62
    Activations Density 0.632%

    No Known Activations