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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2341
    Prev
    Next
    INDEX
    Explanations

    website features and options for user interaction

    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
    1705
    +0.07
    0.2%
    1785
    +0.06
    0.2%
    223
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.07
    0.16
    184
    +0.06
    0.03
    823
    +0.06
    0.11
    Negative Logits
    
    -0.85
    ↵↵
    -0.82
     disarm
    -0.77
     impelled
    -0.77
     reappeared
    -0.76
     vainly
    -0.76
     vanqu
    -0.76
     overtook
    -0.76
     rejoined
    -0.76
      
    -0.76
    POSITIVE LOGITS
     quoique
    1.14
     Ottobre
    1.14
     centrif
    1.14
     ivi
    1.13
     ordina
    1.12
     applau
    1.09
     Perci
    1.09
     Áng
    1.08
     electrica
    1.07
     Giugno
    1.07
    Activations Density 2.834%

    No Known Activations