© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 173
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" indicating intent or purpose

    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
    +0.42
    2.0%
    411
    +0.13
    0.6%
    2019
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.42
    0.07
    1415
    +0.13
    0.07
    411
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.10
    <?
    -0.78
     intersper
    -0.71
    ⓧ
    -0.65
    /**
    -0.58
     endow
    -0.58
     rouse
    -0.58
     disbur
    -0.56
    /***
    -0.56
     gratify
    -0.52
    POSITIVE LOGITS
     soggior
    0.84
     sappi
    0.83
     Palembang
    0.79
     Karang
    0.76
    SBATCH
    0.76
     bandung
    0.75
     eduardo
    0.74
     pymongo
    0.72
     inol
    0.71
     affez
    0.71
    Activations Density 0.310%

    No Known Activations