© 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. 2120
    Prev
    Next
    INDEX
    Explanations

    phrases related to security systems and repeated actions

    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
    674
    +0.09
    0.3%
    198
    +0.08
    0.2%
    683
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.09
    0.07
    659
    +0.08
    0.06
    1919
    +0.07
    0.05
    Negative Logits
     maske
    -0.68
     kristal
    -0.65
     beton
    -0.64
     logis
    -0.63
     optik
    -0.61
     keramik
    -0.60
     kafe
    -0.60
     balon
    -0.60
     meras
    -0.59
     makro
    -0.57
    POSITIVE LOGITS
     normally
    0.85
     usually
    0.84
     ordinarily
    0.82
     cushi
    0.79
     alway
    0.78
     typically
    0.78
    usually
    0.78
     habitually
    0.77
     hairc
    0.76
    normally
    0.76
    Activations Density 0.640%

    No Known Activations