© 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 EvalsExportsinterp-engineNEWAPI 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. 4902
    Prev
    Next
    INDEX
    Explanations

    information related to specific events and appearances

    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
    1577
    +0.26
    0.9%
    50
    +0.22
    0.8%
    764
    +0.21
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.26
    0.06
    736
    +0.22
    0.10
    382
    +0.21
    0.08
    Negative Logits
     meras
    -0.82
     bolí
    -0.79
     palet
    -0.78
     patin
    -0.78
     tà
    -0.78
     ristor
    -0.78
     locu
    -0.78
     bambu
    -0.78
     teras
    -0.77
     solidar
    -0.75
    POSITIVE LOGITS
     unspeak
    1.40
     shenan
    1.39
     pamph
    1.33
     cuck
    1.32
     apprehen
    1.25
     reconno
    1.24
     sophistic
    1.20
     indestru
    1.19
     disagre
    1.19
     philanth
    1.19
    Activations Density 1.897%

    No Known Activations