© 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. 12540
    Prev
    Next
    INDEX
    Explanations

    technical information related to software, hardware, and financial transactions

    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
    1351
    +0.11
    0.3%
    1325
    +0.10
    0.3%
    1026
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1351
    +0.11
    0.03
    143
    +0.10
    0.03
    1506
    +0.09
    0.03
    Negative Logits
     konkre
    -0.68
     rü
    -0.67
     gili
    -0.67
     keramik
    -0.63
     kompati
    -0.61
     alkoh
    -0.61
     akut
    -0.60
     radikal
    -0.60
     karton
    -0.59
     kön
    -0.59
    POSITIVE LOGITS
    nemia
    0.70
     onely
    0.68
     liberality
    0.64
     Mostly
    0.63
    Mostly
    0.60
     Ministero
    0.58
    membrance
    0.57
     mostly
    0.57
     muualla
    0.57
     unwarran
    0.56
    Activations Density 0.122%

    No Known Activations