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. 773
    Prev
    Next
    INDEX
    Explanations

    phrases indicating research studies and their methodologies

    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
    +0.25
    0.9%
    1757
    +0.15
    0.5%
    1350
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1350
    +0.25
    0.10
    1757
    +0.15
    0.10
    1296
    +0.15
    0.07
    Negative Logits
    <bos>
    -1.50
    Cringe
    -0.72
     assiste
    -0.70
     confirme
    -0.65
    Fuckin
    -0.58
     feign
    -0.57
     croit
    -0.56
     constate
    -0.56
    /***
    
    -0.55
     captiv
    -0.54
    POSITIVE LOGITS
     maroc
    1.02
     unwarran
    1.01
     Keny
    0.99
     Hez
    0.94
     bahay
    0.93
     kani
    0.91
     saad
    0.90
     bagay
    0.90
     mikrofon
    0.89
     susun
    0.89
    Activations Density 2.327%

    No Known Activations