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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12978
    Prev
    Next
    INDEX
    Explanations

    phrases related to making up for something or compensating for past actions or events

    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
    1757
    +0.18
    0.7%
    674
    +0.15
    0.5%
    544
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1757
    +0.18
    0.03
    568
    +0.15
    0.02
    976
    +0.13
    0.02
    Negative Logits
     accla
    -1.01
     emphat
    -0.98
     embra
    -0.97
     inconce
    -0.96
     fath
    -0.96
     inev
    -0.94
     parch
    -0.92
     desir
    -0.92
     benevol
    -0.91
     unden
    -0.90
    POSITIVE LOGITS
     makeup
    0.93
     Makeup
    0.82
    Makeup
    0.81
    makeup
    0.74
     up
    0.72
     Up
    0.62
    <bos>
    0.61
    up
    0.60
     UP
    0.59
     EconPapers
    0.58
    Activations Density 0.056%

    No Known Activations