© 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. 3437
    Prev
    Next
    INDEX
    Explanations

    terms associated with measurements and sizes

    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
    +0.20
    0.7%
    1910
    +0.10
    0.4%
    1013
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.20
    0.07
    1910
    +0.10
    0.04
    1385
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.44
    //{
    -0.58
     us
    -0.54
     put
    -0.54
     had
    -0.54
     educate
    -0.54
    IActionResult
    -0.52
     activate
    -0.52
     have
    -0.51
    lateinit
    -0.51
    POSITIVE LOGITS
     Minang
    1.33
     sappi
    1.21
     Juf
    1.17
     Keny
    1.15
     shopee
    1.11
     Karang
    1.06
     keramik
    1.05
     blackpink
    1.05
     nuoc
    1.04
     roberto
    1.04
    Activations Density 0.472%

    No Known Activations