© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3375
    Prev
    Next
    INDEX
    Explanations

    locations or places, especially islands and countries

    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
    +0.18
    0.6%
    849
    +0.09
    0.3%
    1506
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.18
    0.06
    356
    +0.09
    0.05
    2047
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.10
    ⓧ
    -0.71
    EndProject
    -0.62
    և
    -0.61
    
    -0.61
    })();
    -0.60
    倒
    -0.60
    Показать
    -0.59
    <?
    -0.58
    bootstrapcdn
    -0.58
    POSITIVE LOGITS
     ecru
    1.70
     ftu
    1.51
     madonna
    1.45
     fta
    1.45
     stockholm
    1.44
     mef
    1.44
     increa
    1.44
     aen
    1.44
     maneu
    1.41
     ftre
    1.41
    Activations Density 0.230%

    No Known Activations