© 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. 14751
    Prev
    Next
    INDEX
    Explanations

    keywords related to occupying or fulfilling a role or position

    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
    878
    +0.11
    0.4%
    1381
    +0.11
    0.4%
    168
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1381
    +0.11
    0.03
    878
    +0.11
    0.03
    168
    +0.10
    0.03
    Negative Logits
     saper
    -0.54
     cammin
    -0.54
     riman
    -0.51
     uniqu
    -0.51
     raso
    -0.50
     marte
    -0.50
     introd
    -0.49
     Legge
    -0.49
     usuf
    -0.48
     sopr
    -0.48
    POSITIVE LOGITS
     fill
    1.37
     fills
    1.29
     filling
    1.29
    fill
    1.26
     Fill
    1.21
     filled
    1.20
    filling
    1.18
     Filling
    1.15
    filled
    1.15
     FILL
    1.14
    Activations Density 0.100%

    No Known Activations