© 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. 5494
    Prev
    Next
    INDEX
    Explanations

    phrases where the concept of interaction or comparison between two subjects is present

    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
    1235
    +0.12
    0.4%
    1671
    +0.11
    0.4%
    1892
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1235
    +0.12
    0.03
    1671
    +0.11
    0.03
    1085
    +0.11
    0.02
    Negative Logits
     TÉCN
    -0.66
    Até
    -0.61
     CONCEP
    -0.61
    Pranala
    -0.59
     LIRE
    -0.59
    Aceite
    -0.58
    ὁ
    -0.56
    ഇ
    -0.56
    Saiba
    -0.55
    Vaata
    -0.55
    POSITIVE LOGITS
     intersper
    0.97
     shenan
    0.97
     unspeak
    0.87
     cuck
    0.84
     indescri
    0.82
     indestru
    0.82
     overcrow
    0.81
     hentai
    0.80
     fucker
    0.80
     horrend
    0.79
    Activations Density 0.055%

    No Known Activations