© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 508
    Prev
    Next
    INDEX
    Explanations

    mentions of new developments or establishments in the community

    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
    +0.30
    1.2%
    1013
    +0.19
    0.8%
    1177
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.30
    0.08
    1120
    +0.19
    0.03
    939
    +0.15
    0.07
    Negative Logits
    <bos>
    -2.02
    ⓧ
    -0.99
    <?
    -0.88
    
    -0.88
    /**
    -0.86
    <?
    -0.82
    /*
    -0.78
    <!--
    -0.68
    <>
    -0.66
    /*++
    -0.64
    POSITIVE LOGITS
     délib
    0.85
     catég
    0.84
     Juf
    0.78
     Jambi
    0.76
     Khart
    0.76
     Cár
    0.74
     prét
    0.74
     Gorb
    0.73
     Minang
    0.73
     Palembang
    0.71
    Activations Density 0.510%

    No Known Activations