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. 6815
    Prev
    Next
    INDEX
    Explanations

    information regarding sports rankings and performance in specific competitions

    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
    1967
    +0.22
    0.8%
    1438
    +0.15
    0.6%
    1741
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1987
    +0.22
    0.13
    562
    +0.15
    0.10
    498
    +0.13
    0.09
    Negative Logits
    <bos>
    -2.12
     disambiguazione
    -0.99
     demurrer
    -0.94
     schoolmaster
    -0.93
     torte
    -0.91
    GEBURTSDATUM
    -0.91
     CARTOON
    -0.91
     papà
    -0.87
    raught
    -0.87
     nutella
    -0.86
    POSITIVE LOGITS
     rafra
    0.70
     inégal
    0.65
     bross
    0.64
     téléph
    0.64
    kuper
    0.64
     peup
    0.63
     mû
    0.63
     alté
    0.63
     regroupe
    0.62
     Spes
    0.62
    Activations Density 1.442%

    No Known Activations