© 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. 1989
    Prev
    Next
    INDEX
    Explanations

    sections related to scientific research and experiments

    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
    1577
    +0.34
    1.3%
    964
    +0.19
    0.7%
    50
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.34
    0.25
    184
    +0.19
    0.03
    453
    +0.13
    0.18
    Negative Logits
     <<<<<<<<<<<<<<
    -0.85
    ==""){
    -0.78
     Vikipedi
    -0.75
    kháu
    -0.74
    =="")
    -0.73
    SneakyThrows
    -0.71
    ]=>
    -0.70
     miseria
    -0.69
    !="")
    -0.68
    ImageContext
    -0.67
    POSITIVE LOGITS
     impra
    1.28
     depic
    1.17
     inev
    1.17
     reluct
    1.17
     uninten
    1.15
     secon
    1.15
     shenan
    1.14
     affor
    1.13
     Intere
    1.09
     increa
    1.09
    Activations Density 6.661%

    No Known Activations