© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6968
    Prev
    Next
    INDEX
    Explanations

    phrases related to addressing and dealing with situations, especially when involving serious matters or children

    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
    1553
    +0.08
    0.2%
    1984
    +0.08
    0.2%
    674
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.08
    0.06
    284
    +0.08
    0.06
    1055
    +0.08
    0.05
    Negative Logits
     depic
    -2.43
     encomp
    -2.42
     increa
    -2.42
     maneu
    -2.38
     inev
    -2.38
     reluct
    -2.36
     disagre
    -2.35
     guarante
    -2.33
     accla
    -2.30
     emphat
    -2.26
    POSITIVE LOGITS
     differently
    0.93
     correctly
    0.87
     properly
    0.86
     without
    0.79
    InitVars
    0.79
    ciatore
    0.78
     efficiently
    0.77
     muualla
    0.75
     Walkover
    0.73
    TagMode
    0.73
    Activations Density 0.410%

    No Known Activations