© 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. 2217
    Prev
    Next
    INDEX
    Explanations

    references to natural landscapes and conservation efforts

    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
    1120
    +0.17
    0.5%
    939
    +0.15
    0.5%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.17
    0.06
    1499
    +0.15
    0.04
    227
    +0.10
    0.05
    Negative Logits
     geforce
    -1.21
     logitech
    -1.02
     ryzen
    -0.92
    YMMV
    -0.85
     razer
    -0.79
     stik
    -0.78
     toshiba
    -0.77
     incess
    -0.75
     assiste
    -0.73
     disreg
    -0.72
    POSITIVE LOGITS
     conservation
    0.73
     protected
    0.68
     Conservation
    0.66
     preservation
    0.64
     parks
    0.60
    protected
    0.58
     park
    0.57
     preserve
    0.57
     wildlife
    0.57
     preserves
    0.56
    Activations Density 0.329%

    No Known Activations