© 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. 11053
    Prev
    Next
    INDEX
    Explanations

    information related to a space mission or space-related events

    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
    946
    +0.10
    0.3%
    674
    +0.10
    0.3%
    856
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1088
    +0.10
    0.05
    655
    +0.10
    0.05
    300
    +0.10
    0.05
    Negative Logits
     affez
    -1.00
     applau
    -0.91
     gius
    -0.90
     peppa
    -0.87
     dicono
    -0.86
     espri
    -0.83
     ripet
    -0.82
     daz
    -0.78
     abbra
    -0.77
     hairc
    -0.77
    POSITIVE LOGITS
     Thursday
    0.61
     Tuesday
    0.57
     Friday
    0.56
     Wednesday
    0.55
     Saturday
    0.54
     today
    0.54
     yesterday
    0.54
     tonight
    0.53
     Monday
    0.53
     pm
    0.51
    Activations Density 0.140%

    No Known Activations