© 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. 6851
    Prev
    Next
    INDEX
    Explanations

    questioning phrases or quotations

    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
    964
    +0.22
    0.6%
    453
    +0.12
    0.3%
    1445
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.22
    0.05
    981
    +0.12
    0.06
    227
    +0.10
    0.05
    Negative Logits
     maroc
    -0.73
     brava
    -0.72
     ufficio
    -0.69
     milano
    -0.69
     exciter
    -0.68
     tulum
    -0.67
     soggior
    -0.66
     auguri
    -0.64
     virtù
    -0.64
     colombia
    -0.63
    POSITIVE LOGITS
    <bos>
    0.86
    Ekster
    0.66
    calciatore
    0.65
    lepiej
    0.63
    Glej
    0.63
    awtextra
    0.63
    Serviço
    0.62
    Життєпис
    0.62
    Bjs
    0.61
    conio
    0.61
    Activations Density 0.358%

    No Known Activations