© 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. 12817
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical documentation or procedures, specifically involving detailed technical terms and instructions

    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
    1870
    +0.19
    0.6%
    1535
    +0.17
    0.6%
    678
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.19
    0.09
    1467
    +0.17
    0.05
    1490
    +0.14
    0.07
    Negative Logits
    <bos>
    -1.68
     (
    -0.73
    .
    -0.72
    ,
    -0.71
    FailureListener
    -0.68
     in
    -0.67
     
    -0.66
     pinulongan
    -0.66
     In
    -0.65
    ...
    -0.64
    POSITIVE LOGITS
     abnorm
    1.67
     erec
    1.66
     dises
    1.64
     bandung
    1.61
     pessi
    1.54
     canel
    1.52
     socie
    1.52
     milano
    1.51
     imposs
    1.50
     igno
    1.50
    Activations Density 0.751%

    No Known Activations