© 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. 0-RES-JB
    11. 2566
    Prev
    Next
    INDEX
    Explanations

    locations or names of towns and cities

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    82
    +0.10
    0.3%
    1974
    +0.09
    0.3%
    1604
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.03
    844
    +0.09
    0.03
    1256
    +0.08
    0.02
    Negative Logits
    guang
    -0.81
    xiu
    -0.81
    qiao
    -0.79
     itong
    -0.72
    zhong
    -0.71
    xiang
    -0.69
    sheng
    -0.67
     kahit
    -0.61
     akong
    -0.60
    yue
    -0.60
    POSITIVE LOGITS
    han
    2.73
    HAN
    2.05
     HAN
    1.56
    Han
    1.47
     affor
    1.35
     Han
    1.33
     han
    1.31
     maneu
    1.30
     impra
    1.27
    hans
    1.24
    Activations Density 0.183%

    No Known Activations