© 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. 4141
    Prev
    Next
    INDEX
    Explanations

    steps or instructions in a process

    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
    1150
    +0.13
    0.4%
    1336
    +0.12
    0.4%
    297
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.13
    0.05
    1336
    +0.12
    0.04
    872
    +0.12
    0.05
    Negative Logits
    Espèce
    -0.63
    indicato
    -0.51
    tamen
    -0.50
    dicionado
    -0.50
    emptory
    -0.50
     NKC
    -0.49
    cillor
    -0.49
     חיצוניים
    -0.48
     disambiguazione
    -0.48
     meras
    -0.48
    POSITIVE LOGITS
     steps
    0.88
     Steps
    0.87
     stepwise
    0.83
     procedure
    0.83
    Steps
    0.82
    steps
    0.80
     process
    0.79
     Procedure
    0.77
    Procedure
    0.76
    Procedures
    0.75
    Activations Density 0.492%

    No Known Activations