© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 791
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    866
    +0.15
    0.5%
    1101
    +0.11
    0.3%
    950
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.15
    0.04
    1343
    +0.11
    0.04
    690
    +0.09
    0.04
    Negative Logits
    ždý
    -0.76
    <bos>
    -0.67
    GeneratedMessage
    -0.62
     av
    -0.62
     ar
    -0.60
    compose
    -0.60
     won
    -0.60
     ин
    -0.59
     рас
    -0.59
    zydent
    -0.59
    POSITIVE LOGITS
     Bailey
    2.48
     bailey
    2.33
    Bailey
    2.15
     emphat
    1.82
     increa
    1.77
     Baile
    1.77
     accla
    1.77
     affor
    1.73
     disagre
    1.70
     inev
    1.70
    Activations Density 0.279%

    No Known Activations