© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 78
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.21
    0.9%
    1177
    +0.16
    0.7%
    1343
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.21
    0.04
    1343
    +0.16
    0.06
    1828
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.66
    一
    -0.76
    /**
    -0.75
    /**
    -0.75
    </tbody>
    -0.71
    而
    -0.70
    й
    -0.69
    getClassLoader
    -0.69
    .
    -0.68
     могат
    -0.68
    POSITIVE LOGITS
     affor
    2.10
     maneu
    2.08
     impra
    2.08
     intermitt
    2.05
     increa
    2.03
     wikihow
    2.00
     scrat
    1.96
     strick
    1.95
     emphat
    1.93
     eiffel
    1.87
    Activations Density 0.360%

    No Known Activations