© 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. 2569
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a statement or quote from a person

    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
    0.8%
    1265
    +0.13
    0.6%
    453
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.17
    0.12
    2034
    +0.13
    0.10
    382
    +0.11
    0.08
    Negative Logits
     intersper
    -1.50
    <bos>
    -1.38
     quitted
    -1.27
     encomp
    -1.24
     Gorb
    -1.23
     McLaugh
    -1.22
     unve
    -1.21
     reluct
    -1.17
     Thier
    -1.17
     Mlle
    -1.17
    POSITIVE LOGITS
    :]:
    0.71
    nonzero
    0.70
     Crosse
    0.67
    --]
    0.67
    "");
    0.66
    "}")
    0.66
     miniatura
    0.64
    :].
    0.61
     فريبيس
    0.60
    textTheme
    0.60
    Activations Density 1.544%

    No Known Activations