Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 811
    Prev
    Next
    INDEX
    Explanations

    references to political actions related to science and legal processes

    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
    +0.34
    1.4%
    1577
    +0.19
    0.8%
    1842
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.34
    0.14
    1385
    +0.19
    0.11
    998
    +0.15
    0.07
    Negative Logits
    <bos>
    -2.14
     intersper
    -1.13
     encomp
    -0.81
     shenan
    -0.80
     chanced
    -0.77
     mustered
    -0.77
    /***
    
    -0.76
     endow
    -0.74
     enshr
    -0.73
     disambigu
    -0.73
    POSITIVE LOGITS
     soggior
    0.76
     cioc
    0.76
     croce
    0.74
    />";
    0.73
     ceramica
    0.72
     adatta
    0.71
     particolar
    0.69
     indiri
    0.67
    €/
    0.67
     mangiare
    0.67
    Activations Density 2.838%

    No Known Activations