© 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. 289
    Prev
    Next
    INDEX
    Explanations

    words related to a specific technical software or tool, possibly related to graphics or visual effects

    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
    1339
    +0.08
    0.2%
    9
    +0.08
    0.2%
    1671
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.04
    1363
    +0.08
    0.02
    1896
    +0.08
    0.02
    Negative Logits
     vandaag
    -0.70
     overtook
    -0.68
     liever
    -0.67
     måske
    -0.64
     uiteindelijk
    -0.63
     verwacht
    -0.63
     swelled
    -0.62
     glowed
    -0.62
     shrank
    -0.62
     lingered
    -0.62
    POSITIVE LOGITS
     Nu
    2.91
    Nu
    2.78
     nu
    2.46
    nu
    2.25
     NU
    1.99
    NU
    1.84
     nus
    1.49
     Nü
    1.33
     nue
    1.26
     Nus
    1.17
    Activations Density 0.263%

    No Known Activations