© 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. 1865
    Prev
    Next
    INDEX
    Explanations

    scientific research findings regarding health and well-being

    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
    1253
    +0.18
    0.5%
    2034
    +0.12
    0.3%
    1535
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.18
    0.06
    610
    +0.12
    0.06
    1959
    +0.10
    0.06
    Negative Logits
     كومونز
    -0.56
     theolog
    -0.56
     solidar
    -0.54
     auguri
    -0.53
     piña
    -0.52
     يتيمه
    -0.52
     misa
    -0.51
     Reichstag
    -0.51
     fidanz
    -0.51
     spalle
    -0.50
    POSITIVE LOGITS
     apprehen
    0.96
     intrigu
    0.88
     shenan
    0.83
     unspeak
    0.81
     disagre
    0.80
     intersper
    0.76
     pooh
    0.75
     overcrow
    0.75
     depic
    0.73
     impelled
    0.73
    Activations Density 0.433%

    No Known Activations