© 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. 3051
    Prev
    Next
    INDEX
    Explanations

    references to specific groups, events, and calculations related to politics and gaming

    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
    +0.25
    0.8%
    289
    +0.07
    0.2%
    270
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1795
    +0.25
    0.06
    1796
    +0.07
    0.04
    2042
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.19
    /***
    -0.54
    nadequate
    -0.53
     abstra
    -0.50
     dras
    -0.50
    […]
    -0.49
    MarshalTo
    -0.49
     fos
    -0.47
    ⓧ
    -0.47
    __*/
    -0.47
    POSITIVE LOGITS
     paradiso
    0.96
     bosco
    0.87
    capulco
    0.83
     ajustable
    0.82
     lupo
    0.81
     ¡¡
    0.81
     Simplemente
    0.78
     fiore
    0.77
     multicolore
    0.76
    lindo
    0.75
    Activations Density 1.313%

    No Known Activations