© 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. 3940
    Prev
    Next
    INDEX
    Explanations

    negative rhetorical questions or expressions of doubt about social norms

    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
    +0.21
    0.8%
    789
    +0.10
    0.4%
    1520
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1082
    +0.21
    0.02
    1743
    +0.10
    0.02
    900
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.04
    StringBuilder
    -0.60
    /***
    -0.60
    resultMap
    -0.58
    RÉ
    -0.58
    modelBuilder
    -0.57
    ToTable
    -0.56
    <?
    -0.56
    Autoritní
    -0.55
     Rama
    -0.55
    POSITIVE LOGITS
     paradiso
    0.95
    velyn
    0.86
     vinci
    0.85
     frito
    0.84
     moreno
    0.82
     sophistic
    0.82
     maneu
    0.82
     bandung
    0.81
     luxuriant
    0.80
     indestru
    0.77
    Activations Density 0.070%

    No Known Activations