© 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. 2793
    Prev
    Next
    INDEX
    Explanations

    specific names and proper nouns associated with brands or 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
    453
    +0.12
    0.4%
    678
    +0.12
    0.4%
    1156
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1798
    +0.12
    0.07
    678
    +0.12
    0.08
    562
    +0.12
    0.07
    Negative Logits
    <bos>
    -1.34
     TECHNIQUE
    -0.88
     DEFENDANT
    -0.86
     sprawy
    -0.82
     Wirkungen
    -0.76
     INVOLVED
    -0.76
     tört
    -0.76
     DISEASES
    -0.73
    /**
    -0.72
     tæt
    -0.71
    POSITIVE LOGITS
     immen
    1.45
     rassemble
    1.38
     renou
    1.38
     simplif
    1.35
     prét
    1.35
     espé
    1.33
     prétend
    1.32
     démoc
    1.30
     gouver
    1.30
     pié
    1.28
    Activations Density 0.449%

    No Known Activations