Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1085
    Prev
    Next
    INDEX
    Explanations

    instances of the word "different."

    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
    +0.25
    1.3%
    421
    +0.14
    0.7%
    1757
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.25
    0.04
    11
    +0.14
    0.03
    390
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.52
    /***
    
    -0.68
    via
    -0.63
    /*!
    
    -0.61
     em
    -0.60
    glPushMatrix
    -0.59
    open
    -0.57
    glPopMatrix
    -0.57
     se
    -0.57
    glColor
    -0.56
    POSITIVE LOGITS
     jaya
    1.56
     bordeaux
    1.51
     milano
    1.50
     napoli
    1.50
     frankfurt
    1.48
     lidl
    1.48
     brava
    1.48
     eiffel
    1.47
     lele
    1.47
     stockholm
    1.46
    Activations Density 0.052%

    No Known Activations