© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4718
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals

    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
    381
    +0.15
    0.6%
    1535
    +0.11
    0.4%
    1177
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.15
    0.08
    981
    +0.11
    0.07
    1390
    +0.11
    0.06
    Negative Logits
     cushi
    -1.07
     annihilated
    -0.95
     interposed
    -0.86
     moistened
    -0.86
     mottled
    -0.86
     disambigu
    -0.86
     sessile
    -0.85
     hentai
    -0.84
     scaly
    -0.84
     unsus
    -0.83
    POSITIVE LOGITS
     karton
    1.59
     silikon
    1.58
     Kategor
    1.58
     antik
    1.57
     mikrofon
    1.54
     keramik
    1.51
     makro
    1.47
     quoique
    1.44
     Strukt
    1.44
     optik
    1.43
    Activations Density 0.270%

    No Known Activations