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

    Neuronpedia

    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. 4485
    Prev
    Next
    INDEX
    Explanations

    astronomical terms and hockey-related words

    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
    856
    +0.12
    0.4%
    738
    +0.11
    0.4%
    394
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.12
    0.07
    1792
    +0.11
    0.08
    1959
    +0.08
    0.12
    Negative Logits
    bootstrapcdn
    -0.57
    IsContent
    -0.55
    thâu
    -0.55
     SwitchCompat
    -0.55
    jspx
    -0.51
    archiviato
    -0.51
    AddTagHelper
    -0.49
    TagMode
    -0.48
    RectangleBorder
    -0.48
    levelse
    -0.47
    POSITIVE LOGITS
     accla
    1.09
     encomp
    1.09
     intermitt
    1.01
     Intere
    1.01
     practition
    0.99
     resear
    0.99
     emphat
    0.98
     Juf
    0.96
     inev
    0.94
     volunte
    0.94
    Activations Density 3.357%

    No Known Activations