Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 735
    Prev
    Next
    INDEX
    Explanations

    terms related to altitude and elevation measurements

    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
    +0.25
    1.0%
    1385
    +0.19
    0.8%
    906
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.25
    0.09
    906
    +0.19
    0.01
    1013
    +0.14
    0.06
    Negative Logits
    <bos>
    -1.99
    ⓧ
    -0.98
    /**
    -0.89
    
    
    -0.78
    /*
    -0.75
    Obrázky
    -0.72
     dras
    -0.68
    <?
    
    -0.67
    sizeCache
    -0.65
    <?
    -0.64
    POSITIVE LOGITS
     pandan
    1.12
     swarovski
    1.09
     getHeight
    1.03
     malheureux
    1.03
     despotism
    1.01
     impractica
    1.01
     genshin
    0.99
     ecru
    0.98
     Bartholo
    0.97
     mépris
    0.97
    Activations Density 0.404%

    No Known Activations