© 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. 1867
    Prev
    Next
    INDEX
    Explanations

    strong emotions and relationships described in a dramatic or intense manner

    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
    +0.10
    0.3%
    382
    +0.10
    0.3%
    227
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.10
    0.07
    717
    +0.10
    0.04
    1533
    +0.09
    0.02
    Negative Logits
     makro
    -1.13
     teras
    -1.10
     umo
    -1.07
     kram
    -1.06
     antik
    -1.05
     elek
    -1.03
     lele
    -1.02
     solidar
    -1.02
     behar
    -1.01
     kamb
    -1.01
    POSITIVE LOGITS
     unspeak
    0.94
     indescri
    0.77
     indestru
    0.75
     disagre
    0.73
     loveliness
    0.73
     impelled
    0.73
     endeavouring
    0.69
     reluct
    0.69
     vainly
    0.68
     accla
    0.68
    Activations Density 0.747%

    No Known Activations