© 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. 13225
    Prev
    Next
    INDEX
    Explanations

    family-related words and phrases

    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
    394
    +0.08
    0.2%
    612
    +0.07
    0.2%
    1967
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    862
    +0.08
    0.02
    513
    +0.07
    0.03
    1093
    +0.07
    0.04
    Negative Logits
     idr
    -1.06
     reluct
    -1.04
     „,
    -1.04
     maneu
    -1.04
     kask
    -1.02
     gmbh
    -1.00
     effe
    -0.99
     mef
    -0.97
     wien
    -0.97
     socie
    -0.97
    POSITIVE LOGITS
     killed
    0.57
     attending
    0.54
     registered
    0.52
     enrolled
    0.52
     involved
    0.51
     abroad
    0.50
     who
    0.49
     whom
    0.49
     deceased
    0.48
     тоже
    0.47
    Activations Density 0.362%

    No Known Activations