© 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. 11291
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to actions, observations, and strategies

    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
    +0.19
    0.6%
    604
    +0.14
    0.4%
    382
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.19
    0.07
    1519
    +0.14
    0.04
    1664
    +0.09
    0.03
    Negative Logits
     sterke
    -0.61
     apprehen
    -0.57
     Ahh
    -0.53
     rígida
    -0.53
    ()?;
    -0.53
     unspeak
    -0.51
     débil
    -0.51
     sterk
    -0.50
     Speaks
    -0.50
     frág
    -0.50
    POSITIVE LOGITS
     ritard
    1.05
     sappi
    1.04
     ridu
    0.98
     abbra
    0.97
     soggior
    0.91
     felici
    0.90
     uncin
    0.86
     incess
    0.86
     credere
    0.84
     affez
    0.84
    Activations Density 0.641%

    No Known Activations