© 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. 1280
    Prev
    Next
    INDEX
    Explanations

    phrases related to open access and copyright licensing

    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
    453
    +0.20
    0.7%
    1343
    +0.13
    0.5%
    50
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.20
    0.03
    453
    +0.13
    0.03
    924
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.96
    Lugares
    -0.82
    Flere
    -0.82
     per
    -0.81
    خواندن
    -0.81
     later
    -0.78
    diferentes
    -0.77
    क्या
    -0.76
     do
    -0.76
     fix
    -0.76
    POSITIVE LOGITS
     ?...
    2.29
     wien
    2.19
     stockholm
    2.19
     milano
    2.15
     !...
    2.10
     accla
    2.07
     emphat
    2.06
     ordina
    2.04
     inder
    2.03
     dispen
    2.03
    Activations Density 0.062%

    No Known Activations