© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6016
    Prev
    Next
    INDEX
    Explanations

    verbs related to daily routines

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    674
    +0.08
    0.2%
    1547
    +0.07
    0.2%
    1468
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1724
    +0.08
    0.04
    586
    +0.07
    0.03
    346
    +0.07
    0.03
    Negative Logits
     intersper
    -1.50
     depic
    -1.39
     encomp
    -1.36
     unspeak
    -1.27
     snoopy
    -1.24
     increa
    -1.23
     hairc
    -1.22
     maneu
    -1.22
     fuf
    -1.21
     disagre
    -1.21
    POSITIVE LOGITS
     again
    1.57
    again
    1.43
    Again
    1.19
     novamente
    1.17
     Again
    1.15
     AGAIN
    1.15
     다시
    1.08
     nuevamente
    1.05
    AGAIN
    1.02
     wieder
    1.00
    Activations Density 0.500%

    No Known Activations