© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1507
    Prev
    Next
    INDEX
    Explanations

    references to events occurring in specific locations or contexts

    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
    +0.32
    1.8%
    1671
    +0.11
    0.6%
    1983
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.32
    0.02
    1983
    +0.11
    0.02
    1413
    +0.10
    0.01
    Negative Logits
    <bos>
    -3.18
    public
    -0.71
    var
    -0.65
    if
    -0.64
    //
    -0.64
    /**
    -0.63
    ništ
    -0.63
     want
    -0.62
    add
    -0.62
    /**
    
    -0.62
    POSITIVE LOGITS
     maneu
    1.94
     milf
    1.93
     disagre
    1.89
     affor
    1.87
     reluct
    1.86
     ftu
    1.86
     fortn
    1.84
     ecru
    1.80
     madonna
    1.79
     fta
    1.78
    Activations Density 0.036%

    No Known Activations