© 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. 3850
    Prev
    Next
    INDEX
    Explanations

    references to specific months, particularly August and March

    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
    +0.15
    0.6%
    1343
    +0.12
    0.5%
    453
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1267
    +0.15
    0.03
    332
    +0.12
    0.03
    776
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.07
    ⓧ
    -1.29
     intersper
    -1.19
    /**
    -1.16
    
    -1.06
     hairc
    -1.02
     disbur
    -1.00
     endow
    -0.99
     gratify
    -0.98
    <?
    -0.96
    POSITIVE LOGITS
     kaos
    0.85
     kosme
    0.83
     keramik
    0.81
     catég
    0.80
     maksi
    0.79
     alkoh
    0.77
     silikon
    0.75
     seksi
    0.75
     praktik
    0.74
     gesta
    0.71
    Activations Density 0.034%

    No Known Activations