© 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. 10963
    Prev
    Next
    INDEX
    Explanations

    text related to programming code structures and explanations

    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
    1741
    +0.15
    0.4%
    184
    +0.14
    0.4%
    1042
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.05
    184
    +0.14
    0.02
    121
    +0.10
    0.04
    Negative Logits
    -------------</
    -0.77
     nawr
    -0.73
    .*")]
    -0.73
    IVEREF
    -0.73
    脚注の使い方
    -0.73
     desertcart
    -0.72
     nakalista
    -0.70
     Italijani
    -0.68
    apropri
    -0.68
    徊
    -0.67
    POSITIVE LOGITS
     increa
    2.38
     fuf
    2.30
     impra
    2.27
     reluct
    2.24
     inev
    2.24
     encomp
    2.22
     guarante
    2.21
     strick
    2.17
     purcha
    2.14
     indestru
    2.11
    Activations Density 0.314%

    No Known Activations