© 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. 13727
    Prev
    Next
    INDEX
    Explanations

    information related to transportation systems, including trains, infrastructure, accidents, and operations

    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
    1842
    +0.15
    0.4%
    609
    +0.14
    0.4%
    1385
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.15
    0.08
    1842
    +0.14
    0.06
    2044
    +0.09
    0.07
    Negative Logits
     inev
    -2.00
     volunte
    -1.98
     emphat
    -1.91
     thut
    -1.89
     depic
    -1.86
     encomp
    -1.85
     accla
    -1.84
     fta
    -1.83
     reluct
    -1.82
     increa
    -1.82
    POSITIVE LOGITS
     without
    1.23
    without
    1.01
     efficiently
    0.88
     ohne
    0.87
     while
    0.85
     WITHOUT
    0.85
     via
    0.83
     Without
    0.83
     safely
    0.83
    ได้
    0.79
    Activations Density 0.592%

    No Known Activations