© 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. 3207
    Prev
    Next
    INDEX
    Explanations

    expressions related to observation and surveillance

    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
    184
    +0.24
    1.1%
    50
    +0.22
    1.0%
    1150
    +0.20
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.24
    0.12
    284
    +0.22
    0.09
    184
    +0.20
    0.03
    Negative Logits
    <bos>
    -3.04
     intersper
    -1.55
     fuf
    -1.39
     encomp
    -1.36
     increa
    -1.35
    /***
    -1.29
     embodi
    -1.27
     emphat
    -1.26
     hairc
    -1.26
     affor
    -1.23
    POSITIVE LOGITS
    .
    0.74
    TimeoutException
    0.65
    ;
    0.65
    .;
    0.64
    newArrayList
    0.63
    ]=="
    0.63
    ."/
    0.63
    VISED
    0.61
    TagHelper
    0.61
     oks
    0.61
    Activations Density 0.684%

    No Known Activations