© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2616
    Prev
    Next
    INDEX
    Explanations

    terms related to IP addresses and their associated information

    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
    +0.21
    1.2%
    1387
    +0.19
    1.1%
    101
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1387
    +0.21
    0.03
    101
    +0.19
    0.02
    404
    +0.13
    0.01
    Negative Logits
    <bos>
    -2.31
    ganu
    -0.59
    sizeCache
    -0.58
    addComponent
    -0.58
    لينكات
    -0.55
    曖昧さ回避
    -0.55
    ContentAlignment
    -0.55
    FunctionFlags
    -0.54
     become
    -0.53
    #![
    -0.53
    POSITIVE LOGITS
     Ip
    1.29
     stockholm
    1.25
     Odys
    1.21
     Juf
    1.19
     IP
    1.19
     Intere
    1.19
     Pamph
    1.18
     IPs
    1.17
     soulign
    1.14
     depic
    1.12
    Activations Density 0.051%

    No Known Activations