© 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. 6847
    Prev
    Next
    INDEX
    Explanations

    references to things being made or created

    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
    1472
    +0.13
    0.5%
    976
    +0.12
    0.5%
    1096
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    976
    +0.13
    0.05
    1472
    +0.12
    0.04
    47
    +0.11
    0.04
    Negative Logits
     kuku
    -0.54
     jati
    -0.53
     kani
    -0.53
     jawa
    -0.50
     jaya
    -0.46
     serai
    -0.45
     susun
    -0.45
    Grath
    -0.45
     bandung
    -0.44
     pylab
    -0.44
    POSITIVE LOGITS
    Made
    1.27
    made
    1.27
     MADE
    1.23
     made
    1.22
     Made
    1.21
    MADE
    1.16
    make
    1.03
    Make
    0.97
    makes
    0.93
    MAKE
    0.92
    Activations Density 0.163%

    No Known Activations