© 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. 11803
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or celebrations

    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
    1323
    +0.18
    0.8%
    122
    +0.14
    0.6%
    1677
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1323
    +0.18
    0.03
    75
    +0.14
    0.02
    1363
    +0.13
    0.03
    Negative Logits
     Mâ
    -0.57
     PLW
    -0.54
     Signor
    -0.54
     Abingdon
    -0.54
     Prato
    -0.54
     chay
    -0.53
     unlaw
    -0.53
     laboring
    -0.53
     pamph
    -0.51
    ristiana
    -0.51
    POSITIVE LOGITS
     Cent
    1.25
     cent
    1.23
     CENT
    1.18
    Cent
    1.16
    cent
    1.06
    CENT
    0.92
     cents
    0.86
     centroid
    0.80
     Cents
    0.79
     centrifuge
    0.78
    Activations Density 0.127%

    No Known Activations