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. 681
    Prev
    Next
    INDEX
    Explanations

    mathematical or logical symbols and their representations

    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
    +0.18
    1.0%
    161
    +0.17
    1.0%
    341
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.18
    0.02
    892
    +0.17
    0.03
    1964
    +0.17
    0.02
    Negative Logits
    <bos>
    -2.59
    
    
    -0.87
    ⓧ
    -0.84
    contentLoaded
    -0.79
    <?
    -0.77
    /**
    -0.74
    Autoritní
    -0.64
    Více
    -0.64
    /*
    -0.62
    @[+][
    -0.61
    POSITIVE LOGITS
     bandung
    1.15
     maroc
    1.12
    ">...
    1.03
     lapin
    0.99
     milano
    0.98
     eiffel
    0.98
     babi
    0.98
     gmbh
    0.98
     swarovski
    0.97
     jawa
    0.97
    Activations Density 0.067%

    No Known Activations