© 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. 2220
    Prev
    Next
    INDEX
    Explanations

    terminology associated with political processes and challenges

    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
    +0.27
    1.1%
    1870
    +0.13
    0.6%
    1265
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.27
    0.07
    342
    +0.13
    0.09
    1485
    +0.09
    0.07
    Negative Logits
    <bos>
    -2.86
     intersper
    -0.99
    /***
    -0.96
    ⓧ
    -0.79
     prochaines
    -0.76
     encomp
    -0.76
    Примеча
    -0.74
     négociations
    -0.74
     strode
    -0.71
     enshr
    -0.71
    POSITIVE LOGITS
     paradiso
    1.04
     croce
    0.98
     montagna
    0.94
     bosco
    0.93
     riva
    0.91
     signora
    0.87
     cavallo
    0.84
     vecchia
    0.84
     villaggio
    0.82
     bellissima
    0.81
    Activations Density 0.872%

    No Known Activations