© 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. 3113
    Prev
    Next
    INDEX
    Explanations

    concepts related to liberty and the implications of freedom

    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
    +0.31
    1.1%
    604
    +0.13
    0.5%
    1553
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1163
    +0.31
    0.04
    804
    +0.13
    0.04
    1791
    +0.09
    0.05
    Negative Logits
    <bos>
    -3.15
    /***
    -0.99
     intersper
    -0.94
    //*/
    -0.85
     endow
    -0.76
    <?
    -0.76
     incarcer
    -0.74
     rouse
    -0.73
     repress
    -0.72
     vanqu
    -0.71
    POSITIVE LOGITS
     riva
    1.22
     santiago
    1.18
     paradiso
    1.17
     mezza
    1.16
     palio
    1.15
     tappa
    1.05
     Jambi
    1.05
     lusso
    1.04
     Pekan
    1.04
     hect
    1.04
    Activations Density 0.661%

    No Known Activations