© 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. 67
    Prev
    Next
    INDEX
    Explanations

    references to varying degrees or levels of something, often in a comparative or analytical context

    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
    +0.15
    0.6%
    1265
    +0.13
    0.5%
    1044
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.15
    0.06
    1705
    +0.13
    0.05
    347
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.68
    ⓧ
    -0.74
    Vegeu
    -0.73
    Adic
    -0.72
    Siga
    -0.67
    Թ
    -0.66
    Sempre
    -0.64
    Matéri
    -0.63
    فيلم
    -0.63
    Embal
    -0.63
    POSITIVE LOGITS
     aen
    1.54
     jaya
    1.52
     levis
    1.47
     wien
    1.46
     lyon
    1.44
     wald
    1.41
     fta
    1.41
     myn
    1.39
     lele
    1.39
     mef
    1.39
    Activations Density 0.413%

    No Known Activations