© 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. 4363
    Prev
    Next
    INDEX
    Explanations

    details related to a specific movie or TV show plot, including characters, actions, and themes

    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
    1842
    +0.25
    0.8%
    184
    +0.13
    0.4%
    2015
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.25
    0.02
    1559
    +0.13
    0.03
    736
    +0.13
    0.05
    Negative Logits
     impra
    -1.48
     suscep
    -1.47
     shenan
    -1.46
     depic
    -1.46
     embodi
    -1.43
     unden
    -1.43
     disreg
    -1.43
     unce
    -1.43
     maneu
    -1.40
     encomp
    -1.39
    POSITIVE LOGITS
     {}));
    0.63
    EndProject
    0.62
    MockBean
    0.62
    Artigo
    0.60
    qtype
    0.59
     Walkover
    0.58
     Bourgoin
    0.58
    postIndex
    0.57
     chng
    0.56
    Debido
    0.56
    Activations Density 0.487%

    No Known Activations