© 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. 444
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports performance

    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
    1978
    +0.15
    0.6%
    50
    +0.14
    0.5%
    1967
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.15
    0.07
    1614
    +0.14
    0.07
    499
    +0.12
    0.06
    Negative Logits
    <bos>
    -1.90
     PLATES
    -0.70
     człowie
    -0.68
    šech
    -0.67
    ;%%
    -0.64
     disarm
    -0.64
    anyuan
    -0.63
    reszcie
    -0.63
     oppress
    -0.63
     sportowe
    -0.63
    POSITIVE LOGITS
     kosme
    1.61
     praktik
    1.57
     silikon
    1.48
     mikrofon
    1.47
     akut
    1.44
     kooper
    1.42
     protokol
    1.42
     minimalis
    1.42
     keramik
    1.40
     alkoh
    1.40
    Activations Density 0.167%

    No Known Activations