© 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. 3651
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming functions and data structures

    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
    +0.22
    0.8%
    876
    +0.17
    0.7%
    1978
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.22
    0.01
    304
    +0.17
    0.00
    1699
    +0.11
    0.06
    Negative Logits
    <bos>
    -2.50
    ⓧ
    -0.78
    Rusia
    -0.76
    Vegeu
    -0.76
    República
    -0.71
    Enllaços
    -0.71
     sofrer
    -0.68
    Perú
    -0.68
    Mujer
    -0.67
    Fuentes
    -0.67
    POSITIVE LOGITS
     effe
    1.94
     wien
    1.92
     parma
    1.79
     inev
    1.76
     opport
    1.75
     stockholm
    1.75
     milano
    1.75
     compen
    1.74
     increa
    1.72
     nece
    1.72
    Activations Density 0.345%

    No Known Activations