© 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. 13452
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and healthcare issues

    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
    382
    +0.16
    0.5%
    1741
    +0.16
    0.5%
    394
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.16
    0.10
    1265
    +0.16
    0.07
    736
    +0.10
    0.07
    Negative Logits
     praktik
    -0.64
     diki
    -0.61
     konsult
    -0.61
     ekst
    -0.61
     antik
    -0.61
    autogui
    -0.59
     pecuni
    -0.59
     meras
    -0.58
     konserv
    -0.57
     stili
    -0.57
    POSITIVE LOGITS
     quitted
    0.85
     vainly
    0.72
     gild
    0.67
     impelled
    0.66
     endeavouring
    0.65
     shuddered
    0.65
     interposed
    0.64
     tolerably
    0.64
     kindled
    0.64
     strove
    0.63
    Activations Density 0.550%

    No Known Activations