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. 767
    Prev
    Next
    INDEX
    Explanations

    technical specifications and terminologies related to processors and performance metrics

    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
    +0.20
    0.8%
    1385
    +0.15
    0.6%
    1042
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.20
    0.08
    1793
    +0.15
    0.04
    498
    +0.13
    0.05
    Negative Logits
    <bos>
    -2.43
    HasIndex
    -0.81
     Italijani
    -0.81
    FormTagHelper
    -0.77
     <<<<<<<<<<<<<<
    -0.74
    glEnable
    -0.74
    addPreferredGap
    -0.74
     ***!
    -0.72
    addComponent
    -0.71
    addGroup
    -0.71
    POSITIVE LOGITS
     emphat
    1.68
     maneu
    1.61
     affor
    1.60
     disgra
    1.53
     aen
    1.51
     practition
    1.51
     reluct
    1.50
     disreg
    1.50
     peppa
    1.48
     sergio
    1.48
    Activations Density 0.493%

    No Known Activations