© 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. 2519
    Prev
    Next
    INDEX
    Explanations

    mentions of certificates or secure documents

    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
    893
    +0.12
    0.7%
    172
    +0.12
    0.6%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.12
    0.06
    1870
    +0.12
    0.04
    783
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.75
    ⓧ
    -0.96
     &___
    -0.81
    AsUp
    -0.78
    DoubleQuotes
    -0.75
    Примеча
    -0.74
    protoimpl
    -0.74
    WithMany
    -0.73
    painel
    -0.72
    Demografía
    -0.72
    POSITIVE LOGITS
     lele
    1.35
     jaya
    1.19
     bandung
    1.13
     nmax
    1.13
     |]
    1.10
     thut
    1.08
     jawa
    1.08
     signora
    1.07
     fua
    1.06
     vne
    1.06
    Activations Density 0.407%

    No Known Activations