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

    Neuronpedia

    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. 1658
    Prev
    Next
    INDEX
    Explanations

    character names and references to narrative elements in storytelling

    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%
    1385
    +0.18
    0.7%
    1013
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.30
    0.08
    1013
    +0.18
    0.06
    1609
    +0.14
    0.04
    Negative Logits
    <bos>
    -2.02
    ⓧ
    -0.88
    <?
    -0.71
    /**
    -0.70
    <?
    -0.65
    
    -0.65
    /*
    -0.63
    💼
    -0.62
     trak
    -0.61
    /*++
    -0.59
    POSITIVE LOGITS
     délib
    1.03
     malheureux
    0.98
     pubg
    0.91
     ninjago
    0.85
     hasbro
    0.85
     genshin
    0.85
     écout
    0.84
     prét
    0.84
     vété
    0.84
     mépris
    0.83
    Activations Density 0.645%

    No Known Activations