© 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. 170
    Prev
    Next
    INDEX
    Explanations

    terms related to logical notation and syntax

    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
    +0.23
    0.9%
    1036
    +0.10
    0.4%
    1013
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.23
    0.09
    1013
    +0.10
    0.12
    1553
    +0.10
    0.09
    Negative Logits
    <bos>
    -2.96
    Autoritní
    -0.67
     ▼
    -0.62
     /**
    -0.62
    Geplaatst
    -0.61
    displayquote
    -0.60
     dè
    -0.58
     donat
    -0.58
    //{
    -0.58
    /*!
    -0.56
    POSITIVE LOGITS
     pymysql
    1.45
     unwarran
    1.22
     ecru
    1.19
     impra
    1.18
     heapq
    1.15
     pylab
    1.14
     împre
    1.12
     psycopg
    1.09
     pymongo
    1.08
     chrysler
    1.07
    Activations Density 1.350%

    No Known Activations