© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 604
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "for."

    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
    1.3%
    58
    +0.11
    0.4%
    313
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.30
    0.03
    254
    +0.11
    0.03
    581
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.79
    /***
    
    -0.85
    /**
    -0.74
    <?
    -0.68
    
    
    -0.67
    ⓧ
    -0.64
    }{||
    -0.64
    lateinit
    -0.59
    /*
    -0.58
    #![
    -0.58
    POSITIVE LOGITS
     jaya
    1.53
     bandung
    1.47
     lele
    1.45
     Minang
    1.35
     jati
    1.33
     jawa
    1.32
     yong
    1.30
     meis
    1.28
     saar
    1.27
     kug
    1.26
    Activations Density 0.146%

    No Known Activations