© 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. 2121
    Prev
    Next
    INDEX
    Explanations

    keywords related to temperature measurement and monitoring

    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
    +0.24
    1.4%
    1491
    +0.12
    0.7%
    1839
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.24
    0.03
    1778
    +0.12
    0.03
    1491
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.58
     intersper
    -1.01
    ⓧ
    -0.94
    /**
    -0.93
     endow
    -0.91
    
    -0.83
    <?
    -0.81
     amass
    -0.80
    <?
    -0.80
     harmonize
    -0.80
    POSITIVE LOGITS
     temperature
    1.22
    temperature
    1.19
     Temperature
    1.14
    Temperature
    1.08
     temperatures
    1.06
     pymysql
    1.03
     psycopg
    0.99
     temperatur
    0.99
     tempfile
    0.97
     pylab
    0.96
    Activations Density 0.042%

    No Known Activations