© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 331
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to significant actions and events

    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
    +0.19
    0.8%
    690
    +0.12
    0.5%
    752
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1871
    +0.19
    0.06
    924
    +0.12
    0.07
    394
    +0.11
    0.07
    Negative Logits
    <bos>
    -2.52
    <?
    -0.87
     чём
    -0.74
     qu
    -0.73
     con
    -0.73
     des
    -0.72
     beat
    -0.71
     set
    -0.71
     defend
    -0.71
     обстоя
    -0.71
    POSITIVE LOGITS
     Chapitre
    1.82
     Kategor
    1.81
     Strukt
    1.75
     Sén
    1.73
     Traité
    1.69
     Etat
    1.68
     applau
    1.68
     rafra
    1.68
     Præ
    1.67
     seksi
    1.67
    Activations Density 0.830%

    No Known Activations