© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3832
    Prev
    Next
    INDEX
    Explanations

    concepts related to hierarchy and ranking systems

    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
    +0.18
    0.6%
    1978
    +0.13
    0.5%
    184
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1080
    +0.18
    0.07
    1978
    +0.13
    0.10
    455
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.76
    Vidite
    -0.89
     汉
    -0.84
    SourceChecksum
    -0.84
    Билгалдахарш
    -0.82
    verifyException
    -0.82
    SharedDtor
    -0.80
    ьаж
    -0.77
    PyExc
    -0.76
    RegressionTest
    -0.73
    POSITIVE LOGITS
     affor
    2.46
     maneu
    2.41
     shenan
    2.38
     reluct
    2.37
     emphat
    2.35
     increa
    2.33
     inev
    2.32
     disagre
    2.31
     unlaw
    2.22
     accla
    2.22
    Activations Density 1.307%

    No Known Activations