© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1754
    Prev
    Next
    INDEX
    Explanations

    terms related to decay and deterioration

    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
    +0.13
    0.6%
    874
    +0.12
    0.5%
    1896
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.13
    0.02
    1443
    +0.12
    0.02
    1385
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.30
     وتسجيلات
    -0.53
    Lanz
    -0.51
     Charles
    -0.51
    push
    -0.51
    <
    -0.51
    <!--<
    -0.51
     ngăn
    -0.50
     seek
    -0.50
    address
    -0.50
    POSITIVE LOGITS
     ftu
    1.20
     fatis
    1.19
     fays
    1.17
     carrefour
    1.15
     »>
    1.14
     levis
    1.13
     aen
    1.12
     laft
    1.12
     fta
    1.11
     jaya
    1.10
    Activations Density 0.106%

    No Known Activations