© 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. 11768
    Prev
    Next
    INDEX
    Explanations

    economic data such as average annual wages in different regions or industries

    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
    +0.43
    1.5%
    394
    +0.20
    0.7%
    1108
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.43
    0.18
    764
    +0.20
    0.12
    895
    +0.15
    0.09
    Negative Logits
    TagMode
    -0.67
    الدراسه
    -0.62
    wavering
    -0.58
    relenting
    -0.56
    Kiedy
    -0.52
    thinkable
    -0.52
    eniably
    -0.51
    sightly
    -0.51
    mistak
    -0.51
    paralleled
    -0.50
    POSITIVE LOGITS
     mef
    1.05
     blos
    0.96
     embodi
    0.96
     daf
    0.95
     meis
    0.93
     daz
    0.92
     vns
    0.90
     effe
    0.90
     §.
    0.89
     wien
    0.89
    Activations Density 2.937%

    No Known Activations