© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4911
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental issues, particularly those involving ecological impact and corporate practices

    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
    196
    +0.15
    0.6%
    1034
    +0.15
    0.6%
    1464
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1034
    +0.15
    0.02
    196
    +0.15
    0.02
    805
    +0.12
    0.02
    Negative Logits
     himo
    -0.60
     hini
    -0.59
     الحره
    -0.55
    WriteBarrier
    -0.53
    testify
    -0.53
    ഊ
    -0.51
    Referencer
    -0.50
    MethodManager
    -0.49
    marle
    -0.49
    Horário
    -0.48
    POSITIVE LOGITS
     maneu
    1.23
     guarante
    1.20
     increa
    1.17
     🤣🤣
    1.17
     impra
    1.15
     Wtf
    1.11
     lmfao
    1.11
     ineffec
    1.10
     wherea
    1.10
     intersper
    1.10
    Activations Density 0.105%

    No Known Activations