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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 577
    Prev
    Next
    INDEX
    Explanations

    quantities related to time and duration

    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
    +0.24
    0.9%
    1978
    +0.14
    0.5%
    776
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.24
    0.07
    1589
    +0.14
    0.05
    1978
    +0.14
    0.05
    Negative Logits
    <bos>
    -2.19
     intersper
    -1.12
     hairc
    -1.02
     encomp
    -0.99
     gaily
    -0.98
     vainly
    -0.93
     vœux
    -0.92
     withal
    -0.90
     quitted
    -0.88
     depic
    -0.86
    POSITIVE LOGITS
     Trasp
    0.83
     Tangerang
    0.77
     Bekasi
    0.74
     jawa
    0.70
     monaster
    0.68
     Lampung
    0.67
     krab
    0.67
     Tugas
    0.65
     Teknik
    0.64
     Jambi
    0.64
    Activations Density 0.121%

    No Known Activations