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. 6796
    Prev
    Next
    INDEX
    Explanations

    information about achievements and records in sports

    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
    +0.24
    0.8%
    1253
    +0.10
    0.3%
    906
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1905
    +0.24
    0.04
    1249
    +0.10
    0.05
    1834
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.06
    BeginInit
    -0.88
    
    -0.86
     AssemblyCompany
    -0.81
     nahilalakip
    -0.79
    ArrowToggle
    -0.75
     <<<<<<<<<<<<<<
    -0.74
    ⓧ
    -0.73
    PerformLayout
    -0.73
    Personendaten
    -0.71
    POSITIVE LOGITS
     maneu
    1.40
     accla
    1.26
     seksi
    1.25
     reluct
    1.23
     attemp
    1.19
     disgra
    1.18
     practition
    1.15
     konsult
    1.13
     praktik
    1.13
     kosme
    1.11
    Activations Density 0.460%

    No Known Activations