© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and protocols

    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
    876
    +0.34
    1.7%
    1842
    +0.24
    1.1%
    50
    +0.20
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.34
    0.00
    678
    +0.24
    0.08
    304
    +0.20
    -0.01
    Negative Logits
    <bos>
    -2.72
    Além
    -1.01
    Apesar
    -1.00
    Ainda
    -0.98
    Referencer
    -0.98
    Pró
    -0.97
    Nº
    -0.97
    Biografi
    -0.97
    Após
    -0.97
    Él
    -0.96
    POSITIVE LOGITS
     wien
    3.38
     aen
    3.33
     effe
    3.30
     increa
    3.29
     affor
    3.28
     dises
    3.22
     mef
    3.19
     milano
    3.18
     stockholm
    3.17
     squa
    3.16
    Activations Density 0.880%

    No Known Activations