© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2301
    Prev
    Next
    INDEX
    Explanations

    technical equipment and devices used for scientific or medical purposes

    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
    +0.34
    1.5%
    1385
    +0.20
    0.8%
    678
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.34
    0.12
    1705
    +0.20
    0.06
    394
    +0.14
    0.08
    Negative Logits
    <bos>
    -2.33
    ⓧ
    -0.80
     realis
    -0.66
    <?
    -0.65
    /***
    -0.63
     disbur
    -0.63
    /**
    -0.63
     rejoin
    -0.59
     spont
    -0.59
    lateinit
    -0.58
    POSITIVE LOGITS
     swarovski
    1.19
     embodi
    1.06
     dégust
    1.05
     ecru
    1.04
     bandung
    1.04
     affari
    1.04
     pollut
    1.02
     olx
    1.00
     appunt
    0.96
     anhyd
    0.96
    Activations Density 1.287%

    No Known Activations