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. 1224
    Prev
    Next
    INDEX
    Explanations

    references to researchers or authors in academic contexts

    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
    1741
    +0.12
    0.5%
    1343
    +0.11
    0.4%
    1531
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.12
    0.08
    1097
    +0.11
    0.08
    1343
    +0.10
    0.07
    Negative Logits
    <bos>
    -2.48
    SerializedName
    -0.76
     onBind
    -0.76
    : 
    -0.74
     nonatomic
    -0.74
    ⓧ
    -0.72
    vantaged
    -0.71
     فہرست
    -0.70
    ctez
    -0.69
    ValueGenerated
    -0.69
    POSITIVE LOGITS
     maneu
    2.28
     accla
    2.24
     disagre
    2.15
     increa
    2.14
     depic
    2.09
     shenan
    2.09
     ftu
    2.03
     reluct
    2.00
     inev
    2.00
     impra
    1.97
    Activations Density 0.264%

    No Known Activations