© 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. 3929
    Prev
    Next
    INDEX
    Explanations

    information related to cybersecurity threats, online privacy, and digital security measures

    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
    2034
    +0.20
    0.6%
    1535
    +0.17
    0.5%
    1150
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.20
    0.08
    1535
    +0.17
    0.07
    827
    +0.14
    0.05
    Negative Logits
     îna
    -0.97
    Lmfao
    -0.91
     flyknit
    -0.89
    pozdrawiam
    -0.85
     amitié
    -0.85
    Cześć
    -0.85
     gsx
    -0.85
     geforce
    -0.84
     Endlich
    -0.84
    Ikr
    -0.83
    POSITIVE LOGITS
     They
    0.73
     Meanwhile
    0.71
     Hopefully
    0.67
     However
    0.65
     The
    0.64
     Their
    0.63
     Maho
    0.61
     But
    0.61
     Also
    0.59
    They
    0.59
    Activations Density 0.442%

    No Known Activations