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. 904
    Prev
    Next
    INDEX
    Explanations

    numerical data associated with statistics and measurements

    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
    +0.27
    1.0%
    297
    +0.08
    0.3%
    615
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.27
    0.06
    615
    +0.08
    0.05
    1499
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.22
    ⓧ
    -0.73
     plak
    -0.72
    
    
    -0.69
     elek
    -0.66
    <?
    -0.65
     lega
    -0.59
     makro
    -0.59
    altri
    -0.58
    /**
    -0.58
    POSITIVE LOGITS
     pymysql
    0.96
     Minang
    0.94
     pymongo
    0.93
    capulco
    0.93
     zipfile
    0.93
     jetta
    0.92
     mondeo
    0.92
     camry
    0.91
     soulign
    0.90
     gsx
    0.90
    Activations Density 0.412%

    No Known Activations