© 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. 3229
    Prev
    Next
    INDEX
    Explanations

    monetary amounts and financial terms related to subscriptions and pricing

    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
    +0.31
    1.4%
    1842
    +0.14
    0.6%
    1343
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.31
    0.14
    1699
    +0.14
    0.10
    304
    +0.11
    -0.01
    Negative Logits
    <bos>
    -2.54
     quitted
    -0.78
    ⓧ
    -0.77
     trod
    -0.76
    /*
    -0.75
     endeavoured
    -0.72
    /**
    -0.71
     strove
    -0.71
    <?
    -0.70
     defray
    -0.70
    POSITIVE LOGITS
     Kategor
    1.22
     lele
    1.19
     kado
    1.17
     keramik
    1.16
     kosme
    1.13
     alkoh
    1.12
     applau
    1.12
     Strukt
    1.11
     silikon
    1.11
     dises
    1.09
    Activations Density 0.816%

    No Known Activations