© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3291
    Prev
    Next
    INDEX
    Explanations

    phrases indicating awareness or knowledge of a situation

    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
    +0.26
    0.9%
    906
    +0.08
    0.3%
    198
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.26
    0.03
    357
    +0.08
    0.03
    1799
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.27
    /**
    -0.70
    
    -0.65
    /*
    -0.65
    ⓧ
    -0.54
     serve
    -0.52
    StringCopy
    -0.52
     became
    -0.51
     endorse
    -0.50
     become
    -0.50
    POSITIVE LOGITS
     Minang
    1.29
     Banjar
    1.21
     Jambi
    1.19
     Muhamma
    1.19
     bandung
    1.13
     jawa
    1.11
     Palembang
    1.10
     jati
    1.09
     Karang
    1.05
     Juf
    1.03
    Activations Density 0.206%

    No Known Activations