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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 849
    Prev
    Next
    INDEX
    Explanations

    objects and items related to living spaces and household fixtures

    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
    +0.26
    1.0%
    1870
    +0.13
    0.5%
    1385
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.26
    0.12
    1013
    +0.13
    0.09
    1870
    +0.12
    0.06
    Negative Logits
    <bos>
    -2.36
     solidar
    -0.81
    /***
    
    -0.81
    ///**
    -0.78
    MessageOf
    -0.74
    HasAnnotation
    -0.74
    TextEditing
    -0.71
     drap
    -0.69
     spontan
    -0.67
    //---
    -0.66
    POSITIVE LOGITS
     embodi
    1.19
    Hahah
    1.02
     Ename
    1.01
     impractica
    0.99
    Noice
    0.98
     Minang
    0.95
    Fitment
    0.95
    Ohhhh
    0.93
     liberality
    0.93
    Ehh
    0.93
    Activations Density 0.727%

    No Known Activations