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. 709
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to philosophy

    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
    +0.20
    1.1%
    966
    +0.11
    0.6%
    950
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    966
    +0.20
    0.02
    950
    +0.11
    0.02
    251
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.64
    AsUp
    -0.74
    writeField
    -0.71
    ⓧ
    -0.69
     convene
    -0.67
     inaugurate
    -0.65
    /***
    
    -0.65
     avert
    -0.62
     conserve
    -0.62
    IContainer
    -0.61
    POSITIVE LOGITS
     affor
    1.26
     increa
    1.21
     thut
    1.14
     wien
    1.13
     bandung
    1.12
     Juf
    1.11
     tew
    1.10
     yong
    1.10
     yoo
    1.10
     FFFF
    1.08
    Activations Density 0.034%

    No Known Activations