© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1267
    Prev
    Next
    INDEX
    Explanations

    phrases indicating differences or comparisons

    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
    +0.17
    0.6%
    1108
    +0.12
    0.4%
    1325
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.17
    0.08
    1243
    +0.12
    0.05
    1305
    +0.09
    0.04
    Negative Logits
    <bos>
    -1.87
     encomp
    -0.81
     intersper
    -0.79
     endeavored
    -0.78
     endeav
    -0.77
     enshr
    -0.76
     endeavouring
    -0.75
     inaugurate
    -0.73
     reluct
    -0.72
     shenan
    -0.71
    POSITIVE LOGITS
     paradiso
    1.03
    ">/
    0.90
     commerciali
    0.89
     particolar
    0.88
     affez
    0.87
    ]**
    0.86
     autunno
    0.85
    limsy
    0.84
     artigian
    0.83
    ">...
    0.83
    Activations Density 0.951%

    No Known Activations