© 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. 12006
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, particularly universities or cities

    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
    1556
    +0.10
    0.3%
    973
    +0.08
    0.3%
    990
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.05
    1043
    +0.08
    0.04
    1556
    +0.08
    0.03
    Negative Logits
     jawa
    -0.69
     bandung
    -0.69
     despotism
    -0.68
     saka
    -0.68
     lele
    -0.65
     kebaya
    -0.63
     uhr
    -0.63
     perfons
    -0.62
     bangkok
    -0.61
     sirup
    -0.60
    POSITIVE LOGITS
    Ņ
    0.79
    Tazama
    0.72
    SEGUIR
    0.70
     coloro
    0.69
     démoc
    0.69
    Morfo
    0.68
    Etimo
    0.67
    Assista
    0.66
    Pranala
    0.65
     témo
    0.65
    Activations Density 0.250%

    No Known Activations