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. 1255
    Prev
    Next
    INDEX
    Explanations

    references to imaginary or fictional concepts

    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
    +0.21
    0.8%
    1363
    +0.09
    0.3%
    314
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.21
    0.04
    872
    +0.09
    0.04
    623
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.20
    
    
    -0.80
    /*!
    
    -0.75
     AssemblyCompany
    -0.73
    /**
    -0.67
    /***
    
    -0.66
    RemoveField
    -0.63
    #
    -0.58
     serve
    -0.56
     leave
    -0.56
    POSITIVE LOGITS
     soggior
    1.17
     oleo
    1.14
     napoli
    1.14
     squa
    1.14
     tramont
    1.13
     pican
    1.11
     ibiza
    1.10
     vito
    1.10
     paradiso
    1.09
     noel
    1.09
    Activations Density 0.234%

    No Known Activations