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. 6757
    Prev
    Next
    INDEX
    Explanations

    names of soccer and American football teams

    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
    184
    +0.22
    0.8%
    1343
    +0.20
    0.7%
    1177
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.22
    0.06
    1343
    +0.20
    0.06
    1965
    +0.17
    0.04
    Negative Logits
    <bos>
    -2.47
    ⓧ
    -1.10
    /**
    -1.00
    
    
    -0.98
    #
    -0.96
    <?
    -0.94
    /*
    -0.92
    bardziej
    -0.88
    <?
    
    -0.85
    Pued
    -0.85
    POSITIVE LOGITS
     lele
    1.63
     bandung
    1.58
     wien
    1.49
     saar
    1.49
     kasa
    1.46
     dises
    1.44
     meis
    1.43
     „,
    1.42
     haup
    1.42
     hina
    1.38
    Activations Density 0.198%

    No Known Activations