© 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 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. 11672
    Prev
    Next
    INDEX
    Explanations

    contractions

    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
    241
    +0.14
    0.5%
    2011
    +0.13
    0.5%
    1671
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.14
    0.04
    1331
    +0.13
    0.04
    1262
    +0.12
    0.03
    Negative Logits
     Pillar
    -0.51
     SDC
    -0.51
     Byp
    -0.49
     Unde
    -0.49
     Widely
    -0.48
     Illuminated
    -0.48
     Defective
    -0.48
     Overcome
    -0.47
     Mitochondrial
    -0.47
     Spreading
    -0.47
    POSITIVE LOGITS
    __'
    0.78
    ividual
    0.69
     soggior
    0.66
    +"'
    0.62
    %'
    0.61
     NKC
    0.61
     auguri
    0.60
    ruly
    0.60
    cuno
    0.59
     chiunque
    0.59
    Activations Density 0.165%

    No Known Activations