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

    Neuronpedia

    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. 454
    Prev
    Next
    INDEX
    Explanations

    references to historical events and movements affecting population dynamics

    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
    +0.26
    1.0%
    1967
    +0.13
    0.5%
    1499
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.26
    0.07
    764
    +0.13
    0.03
    1967
    +0.10
    0.06
    Negative Logits
    <bos>
    -3.35
    IsMutable
    -0.73
    AsUp
    -0.72
    webElementXpaths
    -0.69
     nakalista
    -0.65
    MessageTagHelper
    -0.64
    WireFormatLite
    -0.64
     top
    -0.63
     censiti
    -0.63
    EndGlobalSection
    -0.62
    POSITIVE LOGITS
     Juf
    1.44
     squa
    1.41
     véhic
    1.39
     jaya
    1.36
     toledo
    1.36
     hcm
    1.33
     lyon
    1.31
     increa
    1.31
     maneu
    1.29
     quoique
    1.29
    Activations Density 0.731%

    No Known Activations