© 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. 1847
    Prev
    Next
    INDEX
    Explanations

    mentions of brand names

    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
    168
    +0.08
    0.3%
    1937
    +0.08
    0.3%
    50
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.04
    1622
    +0.08
    0.03
    969
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.20
     could
    -0.70
         
    -0.69
     continue
    -0.69
            
    -0.68
     have
    -0.68
     introduce
    -0.68
     think
    -0.68
     can
    -0.67
          
    -0.67
    POSITIVE LOGITS
     maneu
    2.28
     increa
    2.18
     affor
    2.17
     fortn
    2.13
     impra
    2.07
    li
    2.05
     scrat
    2.03
     accla
    2.02
     depic
    1.99
     wherea
    1.97
    Activations Density 0.149%

    No Known Activations