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. 1065
    Prev
    Next
    INDEX
    Explanations

    numeric values or figures

    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
    +0.24
    1.1%
    1967
    +0.15
    0.7%
    752
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.24
    0.06
    2011
    +0.15
    0.06
    1967
    +0.14
    0.07
    Negative Logits
    <bos>
    -3.58
    ⓧ
    -1.48
    /**
    -1.14
    
    
    -1.05
    <?
    -1.01
     gratify
    -0.91
    /*
    -0.88
     disbur
    -0.83
    /*++
    -0.80
     endow
    -0.79
    POSITIVE LOGITS
     mikrofon
    1.54
     silikon
    1.53
     seksi
    1.52
     kafe
    1.51
     teras
    1.45
     optik
    1.42
     lele
    1.40
     keramik
    1.38
     antik
    1.37
     karton
    1.37
    Activations Density 0.222%

    No Known Activations