© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 226
    Prev
    Next
    INDEX
    Explanations

    emoticons denoting positivity or satisfaction

    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
    896
    +0.09
    0.3%
    650
    +0.08
    0.3%
    82
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.09
    0.04
    1752
    +0.08
    0.02
    896
    +0.08
    0.03
    Negative Logits
     speak
    -0.57
     reduce
    -0.57
     🤣🤣
    -0.57
    Hahahahaha
    -0.57
     spoke
    -0.57
    Lmfao
    -0.55
    Lma
    -0.55
     😩
    -0.54
     remain
    -0.54
     fail
    -0.54
    POSITIVE LOGITS
     :)
    1.30
     Ottobre
    1.21
     tph
    1.20
    :)
    1.15
     Luglio
    1.13
     sappi
    1.10
    ^_^
    1.08
     paradiso
    1.07
    ;;)
    1.06
    :))
    1.05
    Activations Density 0.247%

    No Known Activations