© 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. 2256
    Prev
    Next
    INDEX
    Explanations

    adjectives used to describe specific details or events

    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
    791
    +0.13
    0.4%
    1793
    +0.10
    0.3%
    674
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    791
    +0.13
    0.07
    1793
    +0.10
    0.07
    680
    +0.10
    0.05
    Negative Logits
     indestru
    -1.17
     depic
    -1.15
     reluct
    -1.08
     Daven
    -1.03
     maneu
    -1.00
     inev
    -1.00
     fath
    -0.98
     encomp
    -0.97
     wien
    -0.97
     gild
    -0.96
    POSITIVE LOGITS
    Made
    0.81
    made
    0.77
     made
    0.77
     Made
    0.74
     make
    0.72
    make
    0.71
    Make
    0.71
    MADE
    0.71
    Making
    0.70
     MADE
    0.70
    Activations Density 0.286%

    No Known Activations