© 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. 5701
    Prev
    Next
    INDEX
    Explanations

    words related to considering options, decisions, and possibilities

    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
    1063
    +0.08
    0.2%
    1531
    +0.07
    0.2%
    674
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    707
    +0.08
    0.04
    1104
    +0.07
    0.03
    595
    +0.07
    0.03
    Negative Logits
     karton
    -0.63
     silikon
    -0.61
     kompakt
    -0.58
     geograf
    -0.55
     kosme
    -0.55
     respekt
    -0.55
     handels
    -0.55
     keramik
    -0.55
     kolon
    -0.55
     konserv
    -0.55
    POSITIVE LOGITS
     shewn
    0.93
     tolerably
    0.90
     impra
    0.87
     beaute
    0.84
     inconce
    0.82
     indestru
    0.79
     felicity
    0.79
     perfon
    0.78
     disagre
    0.76
     brilli
    0.75
    Activations Density 0.306%

    No Known Activations