© 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. 3070
    Prev
    Next
    INDEX
    Explanations

    references to drought conditions

    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
    1392
    +0.18
    1.0%
    492
    +0.16
    0.9%
    528
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.18
    0.00
    227
    +0.16
    0.04
    893
    +0.15
    0.02
    Negative Logits
    <bos>
    -1.03
     препратки
    -0.62
     تانيه
    -0.54
    o
    -0.54
    Beno
    -0.53
     ivelany
    -0.52
     Gracie
    -0.50
    Rico
    -0.49
    /***
    -0.49
     Spence
    -0.49
    POSITIVE LOGITS
     sappi
    0.93
     kram
    0.92
     bandung
    0.87
     gmbh
    0.85
     beverly
    0.84
     lele
    0.84
     laci
    0.84
     kaos
    0.83
     maksi
    0.81
     teras
    0.81
    Activations Density 0.229%

    No Known Activations