© 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. 10-RES-JB
    11. 2980
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and markers of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    1.0%
    382
    +0.11
    0.5%
    2034
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.24
    0.12
    2034
    +0.11
    0.12
    2019
    +0.09
    0.09
    Negative Logits
    <bos>
    -2.55
    //});
    -0.69
    endwhile
    -0.69
    /***
    -0.64
    EndGlobalSection
    -0.61
    //};
    -0.60
    <?
    -0.58
     reinstate
    -0.54
     infuse
    -0.53
    //*/
    -0.52
    POSITIVE LOGITS
     toti
    0.96
     soulign
    0.94
     cartier
    0.92
     marea
    0.87
     considér
    0.87
     [''
    0.79
     épu
    0.79
     împre
    0.79
     epoca
    0.76
     particolar
    0.76
    Activations Density 0.880%

    No Known Activations