© 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. 2005
    Prev
    Next
    INDEX
    Explanations

    terms related to acceleration, progress, or speed increase

    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
    +0.25
    1.1%
    1425
    +0.13
    0.6%
    1708
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.25
    0.03
    944
    +0.13
    0.02
    164
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.34
    org
    -0.63
     provide
    -0.62
     Yang
    -0.56
     насеља
    -0.56
     refer
    -0.56
    PrivateRoute
    -0.56
    מב
    -0.56
     Ron
    -0.55
     donate
    -0.55
    POSITIVE LOGITS
     jaya
    1.72
     bandung
    1.65
     territo
    1.63
     lele
    1.58
     saar
    1.53
     Minang
    1.46
     chong
    1.45
     dises
    1.45
     bangkok
    1.43
     jawa
    1.42
    Activations Density 0.140%

    No Known Activations