© 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. 7276
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or activities that involve running or advancement

    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
    410
    +0.15
    0.6%
    47
    +0.13
    0.5%
    1101
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.04
    47
    +0.13
    0.04
    1101
    +0.13
    0.04
    Negative Logits
    usstsein
    -0.49
    domésticos
    -0.48
     MainAxisSize
    -0.47
    stylers
    -0.47
    談社
    -0.46
    eleste
    -0.45
     naz
    -0.45
     հղումներ
    -0.44
     saites
    -0.43
    polazione
    -0.43
    POSITIVE LOGITS
     run
    1.29
     Run
    1.26
    run
    1.25
    Run
    1.25
     RUN
    1.23
     Runs
    1.18
    RUN
    1.17
     nutella
    1.16
    Runs
    1.14
     unspeak
    1.08
    Activations Density 0.096%

    No Known Activations