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. 665
    Prev
    Next
    INDEX
    Explanations

    mentions of technical specifications related to the Linux operating system

    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
    +0.23
    1.1%
    381
    +0.14
    0.7%
    484
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.23
    0.05
    876
    +0.14
    -0.01
    484
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.69
     springfox
    -0.87
    ⓧ
    -0.85
    /**
    -0.81
    
    
    -0.75
    Kontrola
    -0.69
    További
    -0.64
    Spoljašnje
    -0.64
     jakarta
    -0.63
    /*++
    -0.62
    POSITIVE LOGITS
     ananas
    1.08
     abnorm
    1.08
     Manufact
    1.06
     seksi
    1.02
     étr
    1.02
     sord
    0.98
     romantique
    0.98
     maroc
    0.98
     zey
    0.96
     compréhen
    0.96
    Activations Density 0.195%

    No Known Activations