© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13816
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and building processes

    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
    1499
    +0.09
    0.3%
    1336
    +0.09
    0.3%
    297
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.09
    0.07
    919
    +0.09
    0.03
    411
    +0.09
    0.04
    Negative Logits
    JspWriter
    -0.51
    ImageContext
    -0.49
    istolet
    -0.48
     circon
    -0.47
     GeoNames
    -0.47
     cartón
    -0.46
     affez
    -0.46
    glLoad
    -0.46
    равда
    -0.45
     distanciation
    -0.45
    POSITIVE LOGITS
     commenced
    0.77
     undertaken
    0.76
     underway
    0.76
     conducted
    0.70
     begun
    0.66
     Conducted
    0.61
     began
    0.58
     commences
    0.58
    conducted
    0.57
     done
    0.57
    Activations Density 0.392%

    No Known Activations