© 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. 4486
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies, especially planets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    The neuron detects mentions of planetary terms — tokens referring to planets and closely related morphological forms.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    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
    1392
    +0.15
    0.5%
    220
    +0.14
    0.5%
    1222
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.15
    0.03
    1392
    +0.14
    0.03
    421
    +0.13
    0.02
    Negative Logits
     pank
    -0.76
     alha
    -0.76
     valla
    -0.73
     priva
    -0.71
     pira
    -0.71
     elek
    -0.69
     liev
    -0.69
     adal
    -0.69
     lemp
    -0.69
     bont
    -0.68
    POSITIVE LOGITS
     planet
    1.29
    planet
    1.12
    Planet
    1.11
     Planet
    1.11
     planets
    1.00
    planets
    0.90
    Planets
    0.87
     PLANET
    0.86
     planeta
    0.79
     planetary
    0.77
    Activations Density 0.060%

    No Known Activations