© 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. 7503
    Prev
    Next
    INDEX
    Explanations

    descriptions related to astronomical phenomena, particularly neutron stars and black holes

    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
    876
    +0.16
    0.5%
    2015
    +0.11
    0.3%
    736
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.16
    0.06
    724
    +0.11
    0.04
    671
    +0.11
    0.03
    Negative Logits
     Incenti
    -0.77
     Lmao
    -0.75
     Alcalde
    -0.73
     hentai
    -0.73
     dawg
    -0.73
     Mónica
    -0.73
     Compañ
    -0.69
     shenan
    -0.69
     motherfucker
    -0.69
     homie
    -0.68
    POSITIVE LOGITS
     fup
    0.74
     thut
    0.73
     aen
    0.65
     [{\
    0.63
     parámetros
    0.59
     foon
    0.58
     ftu
    0.57
     sii
    0.56
     §.
    0.56
     faid
    0.55
    Activations Density 0.340%

    No Known Activations