© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12285
    Prev
    Next
    INDEX
    Explanations

    words related to instructions and guides

    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
    2019
    +0.12
    0.4%
    47
    +0.11
    0.4%
    1381
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.12
    0.06
    1604
    +0.11
    0.04
    1510
    +0.10
    0.04
    Negative Logits
     obé
    -0.89
     véhic
    -0.87
     Février
    -0.83
     dénon
    -0.81
     écout
    -0.81
     redé
    -0.80
     perpétu
    -0.80
     évit
    -0.79
     déliv
    -0.79
     roul
    -0.79
    POSITIVE LOGITS
     making
    1.09
     providing
    1.09
     creating
    1.09
     getting
    1.08
     doing
    1.05
     having
    1.04
     keeping
    1.04
     putting
    1.03
     bringing
    1.02
     giving
    1.01
    Activations Density 0.484%

    No Known Activations