© 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. 4504
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the availability of options or possibilities for improvement

    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
    +0.39
    2.0%
    1909
    +0.15
    0.7%
    752
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.39
    0.06
    1602
    +0.15
    0.06
    752
    +0.14
    0.05
    Negative Logits
    <bos>
    -2.71
    enumerate
    -0.72
    DockStyle
    -0.70
    base
    -0.69
    itemize
    -0.67
    js
    -0.66
     died
    -0.66
    console
    -0.66
    .
    -0.66
    ,
    -0.65
    POSITIVE LOGITS
     hcm
    1.73
     bandung
    1.72
     stockholm
    1.68
     frankfurt
    1.67
     affor
    1.66
     Juf
    1.66
     Minang
    1.66
     Keny
    1.65
     santiago
    1.64
     eiffel
    1.64
    Activations Density 0.282%

    No Known Activations