© 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. 796
    Prev
    Next
    INDEX
    Explanations

    information related to animal feeding practices and manure usage in farming

    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
    1842
    +0.11
    0.3%
    1013
    +0.10
    0.3%
    198
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.11
    0.03
    198
    +0.10
    0.04
    736
    +0.09
    0.04
    Negative Logits
     poichè
    -0.76
     minimalis
    -0.70
     krab
    -0.70
     dichi
    -0.67
     Wikisource
    -0.65
     kram
    -0.65
     afferma
    -0.64
     lavora
    -0.63
     bergen
    -0.63
     Orgel
    -0.62
    POSITIVE LOGITS
     anhyd
    0.91
     unspeak
    0.72
     impractica
    0.69
     livestock
    0.67
     Confu
    0.67
     disagre
    0.66
     reluct
    0.65
     depic
    0.64
     tolerably
    0.64
     lamella
    0.63
    Activations Density 0.328%

    No Known Activations