© 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. 1419
    Prev
    Next
    INDEX
    Explanations

    terms and conditions related to software licenses and legal disclaimers

    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
    1120
    +0.11
    0.4%
    1553
    +0.10
    0.4%
    1871
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.11
    0.10
    283
    +0.10
    0.01
    823
    +0.10
    0.08
    Negative Logits
    ,
    -1.72
    .
    -1.62
      
    -1.62
    ↵↵
    -1.56
     
    -1.54
     (
    -1.53
    ↵
    -1.53
    <eos>
    -1.52
    ;
    -1.52
     so
    -1.51
    POSITIVE LOGITS
     stockholm
    4.80
     fta
    4.78
     aen
    4.76
     wien
    4.74
     mef
    4.64
     dises
    4.62
     effe
    4.60
     squa
    4.57
     fup
    4.54
     ftu
    4.53
    Activations Density 1.017%

    No Known Activations