© 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. 6566
    Prev
    Next
    INDEX
    Explanations

    numerical steps or 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
    394
    +0.29
    1.0%
    184
    +0.26
    0.9%
    1108
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.29
    0.03
    394
    +0.26
    0.05
    648
    +0.17
    0.02
    Negative Logits
     affor
    -1.23
     gaily
    -1.22
     impra
    -1.22
     depic
    -1.20
     apprehen
    -1.19
     cushi
    -1.19
     disagre
    -1.19
     encomp
    -1.19
     reluct
    -1.18
     scrat
    -1.16
    POSITIVE LOGITS
     Walkover
    0.69
    InputTagHelper
    0.68
    isContained
    0.67
    IsContent
    0.64
     كومونز
    0.63
    TagMode
    0.62
    writeFieldEnd
    0.61
    ContentAsync
    0.61
     ویکی‌پدی
    0.59
    Географиясе
    0.59
    Activations Density 0.443%

    No Known Activations