© 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. 2113
    Prev
    Next
    INDEX
    Explanations

    details about a particular event involving parachutes and potential rescue scenarios

    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
    906
    +0.15
    0.4%
    1385
    +0.10
    0.3%
    736
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.06
    724
    +0.10
    0.03
    623
    +0.10
    0.03
    Negative Logits
     alkoh
    -1.22
     kosme
    -1.11
     fré
    -1.08
     minimalis
    -1.08
     praktik
    -1.05
     biograf
    -1.05
     meras
    -1.05
     ideolog
    -1.05
     maksi
    -1.04
     plak
    -1.03
    POSITIVE LOGITS
     landing
    0.89
     landings
    0.72
     landed
    0.70
     lamella
    0.67
     pymysql
    0.66
     parachute
    0.62
     pylab
    0.61
     falling
    0.61
     fall
    0.61
     woollen
    0.58
    Activations Density 0.314%

    No Known Activations