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. 1805
    Prev
    Next
    INDEX
    Explanations

    names of individuals followed by reporting verbs

    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
    +0.26
    1.1%
    1741
    +0.10
    0.4%
    453
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.26
    0.09
    1919
    +0.10
    0.08
    888
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.47
    <?
    
    -0.96
    ⓧ
    -0.96
    /***
    
    -0.95
     assiste
    -0.85
    
    
    -0.81
    /*!
    
    -0.78
    <?
    -0.72
    ///**
    -0.68
     permu
    -0.67
    POSITIVE LOGITS
     heapq
    0.83
     pymysql
    0.75
     smtplib
    0.70
     ascer
    0.68
     psycopg
    0.67
     pymongo
    0.66
     unlaw
    0.65
     maneu
    0.65
     hashlib
    0.65
     functools
    0.64
    Activations Density 0.165%

    No Known Activations