© 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. 13454
    Prev
    Next
    INDEX
    Explanations

    instructions for making food items, particularly dosa recipes

    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
    297
    +0.11
    0.3%
    1120
    +0.10
    0.3%
    1177
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.11
    0.05
    1551
    +0.10
    0.03
    753
    +0.10
    0.01
    Negative Logits
     Rektor
    -0.82
     Jurist
    -0.72
     Czechos
    -0.72
     ideolog
    -0.71
     triump
    -0.71
     monaster
    -0.70
     Bibl
    -0.70
     Gouver
    -0.70
     Kün
    -0.69
     praktik
    -0.69
    POSITIVE LOGITS
    <bos>
    0.63
     ingredients
    0.62
     rassemble
    0.61
     Ingredients
    0.61
    Ingredients
    0.56
    Ingredi
    0.55
     materials
    0.54
     Preparation
    0.52
     trouva
    0.51
    ingredients
    0.49
    Activations Density 0.235%

    No Known Activations