© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12136
    Prev
    Next
    INDEX
    Explanations

    information related to air pollution and its consequences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    100
    +0.09
    0.3%
    1120
    +0.09
    0.3%
    690
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    914
    +0.09
    0.02
    1499
    +0.09
    0.04
    1048
    +0.09
    0.01
    Negative Logits
    <bos>
    -0.68
    ngdoc
    -0.47
     CreateTagHelper
    -0.42
    tagHelperRunner
    -0.41
    çim
    -0.41
     winked
    -0.41
     amigurumi
    -0.40
    ğine
    -0.40
     =[]
    -0.39
    TagHelpers
    -0.39
    POSITIVE LOGITS
     pollution
    0.90
     pollutants
    0.84
     Pollution
    0.76
    pollution
    0.74
     pollutant
    0.74
     kasa
    0.74
     saar
    0.69
     POLLUTION
    0.67
     naer
    0.66
     sirup
    0.65
    Activations Density 0.272%

    No Known Activations