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. 763
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives that characterize intensity or size

    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
    +0.24
    1.0%
    156
    +0.12
    0.5%
    605
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.24
    0.04
    642
    +0.12
    0.05
    393
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.33
    /***
    
    -0.96
    ///**
    -0.90
     defray
    -0.78
     ratify
    -0.76
     avrebbero
    -0.76
     endow
    -0.74
     intersper
    -0.73
    ⓧ
    -0.71
    <?
    
    -0.70
    POSITIVE LOGITS
     asado
    0.80
    hematical
    0.80
     ados
    0.76
     vinci
    0.74
     maroc
    0.73
    GRAPHS
    0.71
     quoc
    0.71
    lindo
    0.70
     cuit
    0.70
    mistak
    0.70
    Activations Density 0.336%

    No Known Activations